arXiv subjects

Aditya Desai

Publications and source records attributed to Aditya Desai.

At least 19 recordsLinked to original sources

arXiv2026

Inference Time Context Sparsity: Illusion or Opportunity?

Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer contexts and agentic interactions, the compute and memory bottlenecks of attention become increasingly critical, raising the question of whether these constraints are fundamental. Our position is that these constraints are artificial and unnecessary, and that the future of LLM inference lies in extreme but principled sparsity along the context dimension. This position is supported by several strands of empirical and theoretical evidence. First, we find the insistence on dense attention unreasonable, since in a long context a query effectively projects O(N) attention information into a hidden space of dimension d << N, making the process inherently lossy. Second, we perform an extensive study of sparsity in LLMs spanning 20 models across five model families, varying context lengths, and different sparsity levels. We empirically demonstrate a strong trend: current LLMs, despite not being trained for context sparsity, are remarkably robust to inference-time decode sparsity across tasks of varying complexity, including retrieval, multi-hop QA, mathematical reasoning, and agentic coding. Importantly, we also show that current hardware is already sufficient to realize substantial gains from this sparsity. For example, our sparse decode kernels accelerate large-context processing by up to 10x over FlashInfer at 50x sparsity levels on hardware such as the H100. Overall, these results position extreme context sparsity not as a heuristic, but as a principled foundation for LLM inference, training, and architecture design: one that is both feasible and beneficial, and a compelling direction for future systems.

cs.AI↗

arXiv2026

SOCKET: SOft Collision Kernel EsTimator for Sparse Attention

Exploiting sparsity during long-context inference is key to scaling large language models, as attention dominates the cost of autoregressive decoding. Sparse attention reduces this cost by restricting computation to a subset of tokens, but its effectiveness depends on efficient scoring and selection at inference time. We revisit Locality-Sensitive Hashing (LSH) and introduce SOCKET, a SOft Collision Kernel EsTimator that replaces hard bucket matches with probabilistic, similarity-aware aggregation. Traditional LSH yields binary collision signals that limit ranking quality and require substantial memory to perform well. In contrast, soft LSH accumulates graded collision evidence across hash tables, preserving top-k ordering with significantly less memory. This reframes LSH from a candidate generator into a principled scoring kernel for sparse attention. Leveraging this property, SOCKET enables efficient token selection without ad hoc voting and matches or surpasses prior sparse attention methods across multiple long-context benchmarks. With a custom CUDA scoring kernel and a Flash Decode Triton backend, SOCKET achieves up to 1.5$\times$ higher throughput than FlashAttention.

cs.LG↗

arXiv2025

Let the Barbarians In: How AI Can Accelerate Systems Performance Research

Artificial Intelligence (AI) is beginning to transform the research process by automating the discovery of new solutions. This shift depends on the availability of reliable verifiers, which AI-driven approaches require to validate candidate solutions. Research focused on improving systems performance is especially well-suited to this paradigm because system performance problems naturally admit such verifiers: candidates can be implemented in real systems or simulators and evaluated against predefined workloads. We term this iterative cycle of generation, evaluation, and refinement AI-Driven Research for Systems (ADRS). Using several open-source ADRS instances (i.e., OpenEvolve, GEPA, and ShinkaEvolve), we demonstrate across ten case studies (e.g., multi-region cloud scheduling, mixture-of-experts load balancing, LLM-based SQL, transaction scheduling) that ADRS-generated solutions can match or even outperform human state-of-the-art designs. Based on these findings, we outline best practices (e.g., level of prompt specification, amount of feedback, robust evaluation) for effectively using ADRS, and we discuss future research directions and their implications. Although we do not yet have a universal recipe for applying ADRS across all of systems research, we hope our preliminary findings, together with the challenges we identify, offer meaningful guidance for future work as researcher effort shifts increasingly toward problem formulation and strategic oversight. Note: This paper is an extension of our prior work [14]. It adds extensive evaluation across multiple ADRS frameworks and provides deeper analysis and insights into best practices.

cs.SE↗

arXiv2025

vAttention: Verified Sparse Attention

State-of-the-art sparse attention methods for reducing decoding latency fall into two main categories: approximate top-$k$ (and its extension, top-$p$) and recently introduced sampling-based estimation. However, these approaches are fundamentally limited in their ability to approximate full attention: they fail to provide consistent approximations across heads and query vectors and, most critically, lack guarantees on approximation quality, limiting their practical deployment. We observe that top-$k$ and random sampling are complementary: top-$k$ performs well when attention scores are dominated by a few tokens, whereas random sampling provides better estimates when attention scores are relatively uniform. Building on this insight and leveraging the statistical guarantees of sampling, we introduce vAttention, the first practical sparse attention mechanism with user-specified $(\epsilon, \delta)$ guarantees on approximation accuracy (thus, "verified"). These guarantees make vAttention a compelling step toward practical, reliable deployment of sparse attention at scale. By unifying top-$k$ and sampling, vAttention outperforms both individually, delivering a superior quality-efficiency trade-off. Our experiments show that vAttention significantly improves the quality of sparse attention (e.g., $\sim$4.5 percentage points for Llama 3.1 8B Instruct and DeepSeek-R1-Distill-Llama-8B on RULER-HARD), and effectively bridges the gap between full and sparse attention (e.g., across datasets, it matches full model quality with up to 20x sparsity). We also demonstrate that it can be deployed in reasoning scenarios to achieve fast decoding without compromising model quality (e.g., vAttention achieves full model quality on AIME2024 at 10x sparsity with up to 32K token generations). Code: https://github.com/skylight-org/sparse-attention-hub. Webpage: https://sky-light.eecs.berkeley.edu.

cs.LG↗

arXiv2025

Barbarians at the Gate: How AI is Upending Systems Research

Artificial Intelligence (AI) is starting to transform the research process as we know it by automating the discovery of new solutions. Given a task, the typical AI-driven approach is (i) to generate a set of diverse solutions, and then (ii) to verify these solutions and select one that solves the problem. Crucially, this approach assumes the existence of a reliable verifier, i.e., one that can accurately determine whether a solution solves the given problem. We argue that systems research, long focused on designing and evaluating new performance-oriented algorithms, is particularly well-suited for AI-driven solution discovery. This is because system performance problems naturally admit reliable verifiers: solutions are typically implemented in real systems or simulators, and verification reduces to running these software artifacts against predefined workloads and measuring performance. We term this approach as AI-Driven Research for Systems (ADRS), which iteratively generates, evaluates, and refines solutions. Using penEvolve, an existing open-source ADRS instance, we present case studies across diverse domains, including load balancing for multi-region cloud scheduling, Mixture-of-Experts inference, LLM-based SQL queries, and transaction scheduling. In multiple instances, ADRS discovers algorithms that outperform state-of-the-art human designs (e.g., achieving up to 5.0x runtime improvements or 50% cost reductions). We distill best practices for guiding algorithm evolution, from prompt design to evaluator construction, for existing frameworks. We then discuss the broader implications for the systems community: as AI assumes a central role in algorithm design, we argue that human researchers will increasingly focus on problem formulation and strategic guidance. Our results highlight both the disruptive potential and the urgent need to adapt systems research practices in the age of AI.

cs.AI↗

arXiv2025

The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

Large Reasoning Models (LRMs) represent a breakthrough in AI problem-solving capabilities, but their effectiveness in interactive environments can be limited. This paper introduces and analyzes overthinking in LRMs. A phenomenon where models favor extended internal reasoning chains over environmental interaction. Through experiments on software engineering tasks using SWE Bench Verified, we observe three recurring patterns: Analysis Paralysis, Rogue Actions, and Premature Disengagement. We propose a framework to study these behaviors, which correlates with human expert assessments, and analyze 4018 trajectories. We observe that higher overthinking scores correlate with decreased performance, with reasoning models exhibiting stronger tendencies toward overthinking compared to non-reasoning models. Our analysis reveals that simple efforts to mitigate overthinking in agentic environments, such as selecting the solution with the lower overthinking score, can improve model performance by almost 30% while reducing computational costs by 43%. These results suggest that mitigating overthinking has strong practical implications. We suggest that by leveraging native function-calling capabilities and selective reinforcement learning overthinking tendencies could be mitigated. We also open-source our evaluation framework and dataset to facilitate research in this direction at https://github.com/AlexCuadron/Overthinking.

cs.AI↗

arXiv2025

vCache: Verified Semantic Prompt Caching

Semantic caches return cached responses for semantically similar prompts to reduce LLM inference latency and cost. They embed cached prompts and store them alongside their response in a vector database. Embedding similarity metrics assign a numerical score to quantify the similarity between a request and its nearest neighbor prompt from the cache. Existing systems use the same static similarity threshold across all requests to determine whether two prompts can share similar responses. However, we observe that static thresholds do not give formal correctness guarantees, result in unexpected error rates, and lead to suboptimal cache hit rates. This paper proposes vCache, the first verified semantic cache with user-defined error rate guarantees for predictable performance. It employs an online learning algorithm to estimate an optimal threshold for each cached prompt, enabling reliable cache responses without additional training. Our experiments show that vCache consistently meets the specified error bounds while outperforming state-of-the-art static-threshold and fine-tuned embedding baselines with up to 12.5$\times$ higher cache hit and 26$\times$ lower error rates. We release the vCache implementation and four benchmarks to support future research.

cs.LG↗

arXiv2024

HashAttention: Semantic Sparsity for Faster Inference

Leveraging long contexts is crucial for advanced AI systems, but attention computation poses a scalability challenge. While scaled dot-product attention (SDPA) exhibits token sparsity, i.e. only a few pivotal tokens significantly contribute to output, exploiting this sparsity remains challenging. Existing methods either suffer from quality degradation or require substantial additional resources. We show that identifying pivotal tokens is a Maximum Inner Product Search (MIPS) problem. However, existing MIPS solutions are not well-suited for SDPA, as they are not GPU-friendly and often underperform due to the separated query and key distributions. This paper introduces HashAttention, framing pivotal token identification as a recommendation problem. Given a query, HashAttention encodes keys and queries in Hamming space, capturing the required semantic similarity, using learned mapping functions. HashAttention efficiently identifies pivotal tokens for a given query using bitwise operations and computes attention using only these tokens, improving the overall attention efficiency. Trained on generic data, HashAttention reduces tokens used by up to $16\times$ with minimal quality loss, requiring only 32 bits of auxiliary memory per token. Sparsity can be further improved to $32\times$ through task-specific fine-tuning. On A100 GPU, at $32\times$ sparsity, incorporating HashAttention reduces attention latency by up to $4.3\times$ in GPT-FAST and $2.54\times$ in FlashDecode, and achieves up to $3.12\times$ higher throughput for GPT-FAST.

cs.LG↗

arXiv2024

Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation

Adapting pre-trained large language models (LLMs) is crucial but challenging due to their enormous size. Parameter-efficient fine-tuning (PEFT) techniques typically employ additive adapters applied to frozen model weights. To further reduce memory usage, model weights are often compressed through quantization. However, existing PEFT methods often yield suboptimal model quality because they rely on restrictive assumptions, such as low-rank constraints on adapters to limit the number of trainable parameters. We find that sketching, a popular data compression technique, can serve as an efficient LLM adaptation strategy while avoiding the low-rank assumption. We introduce SketchTune, a compressive adaptation strategy that compresses LLM weights into compact fine-tunable sketches, integrating compression and adaptation into a unified framework. This integration eliminates the need for complex two-path computation in existing PEFT techniques, enabling faster and more memory-efficient training and inference. SketchTune is supported by mathematical insights into matrix classes that are better approximated using sketching rather than low-rank methods. Our extensive evaluations with Llama and Mistral models demonstrate that SketchTune outperforms leading PEFT methods across diverse tasks while using substantially smaller base models and comparable trainable parameters. As a highlight, SketchTune outperforms LoRA, DoRA, and S2FT on commonsense and math benchmarks using 2.6-3.5$\times$ smaller base models and exceeds LoftQ in accuracy by 14.48% on GSM8K with 7.3$\times$ fewer trainable parameters. Our code is available at https://github.com/LeanModels/SketchTune.

cs.LG↗

arXiv2024

Determining van der Waals materials' optical and polaritonic properties using cryogenic FTIR micro-spectroscopy

Van-der-Waals materials have been shown to support numerous exotic polaritonic phenomena originating from their layered structures and associated vibrational and electronic properties. This includes emergent polaritonic phenomena, including hyperbolicity and exciton-polariton formation. However, many van-der-Waals materials' unique properties are most prominent at cryogenic temperatures. This presents a particular challenge for polaritonics research, as reliable optical constant data is required for understanding light-matter coupling. For infrared polaritonics (3-100um), the small size of exfoliated flakes makes conventional ellipsometry impossible. This paper presents a cryogenic Fourier transform infrared microscope design constructed entirely from off-the-shelf components and fitting procedures for determining optical constants. We use this microscope to present the first temperature-dependent characterization of the optical properties of hexagonal boron nitride grown with isotopically pure boron. We show that Fabry Perot-type resonances close to the transverse optical phonon show the key temperature-dependent tuning of several parameters. Our full analysis of the infrared dielectric function shows small but significant tuning of the optical constants, which is highly consistent with Raman data from the literature. We then use this dielectric data to perform and analyze the polariton propagation properties, which agree extremely well with published cryogenic scattering-type nearfield microscopy results. In addition to the insights gained into hyperbolic polaritons in hBN, our paper represents a transferable framework for characterizing exfoliated infrared polaritonic materials and other infrared devices. This could accelerate discoveries in other material systems, especially those that are spatially inhomogeneous or cannot be prepared as large single crystals.

physics.optics↗

arXiv2024

IDentity with Locality: An ideal hash for gene sequence search

Gene sequence search is a fundamental operation in computational genomics. Due to the petabyte scale of genome archives, most gene search systems now use hashing-based data structures such as Bloom Filters (BF). The state-of-the-art systems such as Compact bit-slicing signature index (COBS) and Repeated And Merged Bloom filters (RAMBO) use BF with Random Hash (RH) functions for gene representation and identification. The standard recipe is to cast the gene search problem as a sequence of membership problems testing if each subsequent gene substring (called kmer) of Q is present in the set of kmers of the entire gene database D. We observe that RH functions, which are crucial to the memory and the computational advantage of BF, are also detrimental to the system performance of gene-search systems. While subsequent kmers being queried are likely very similar, RH, oblivious to any similarity, uniformly distributes the kmers to different parts of potentially large BF, thus triggering excessive cache misses and causing system slowdown. We propose a novel hash function called the Identity with Locality (IDL) hash family, which co-locates the keys close in input space without causing collisions. This approach ensures both cache locality and key preservation. IDL functions can be a drop-in replacement for RH functions and help improve the performance of information retrieval systems. We give a simple but practical construction of IDL function families and show that replacing the RH with IDL functions reduces cache misses by a factor of 5x, thus improving query and indexing times of SOTA methods such as COBS and RAMBO by factors up to 2x without compromising their quality. We also provide a theoretical analysis of the false positive rate of BF with IDL functions. Our hash function is the first study that bridges Locality Sensitive Hash (LSH) and RH to obtain cache efficiency.

cs.IR↗

arXiv2023

Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspaces

Recommendation systems (RS) for items (e.g., movies, books) and ads are widely used to tailor content to users on various internet platforms. Traditionally, recommendation models are trained on a central server. However, due to rising concerns for data privacy and regulations like the GDPR, federated learning is an increasingly popular paradigm in which data never leaves the client device. Applying federated learning to recommendation models is non-trivial due to large embedding tables, which often exceed the memory constraints of most user devices. To include data from all devices in federated learning, we must enable collective training of embedding tables on devices with heterogeneous memory capacities. Current solutions to heterogeneous federated learning can only accommodate a small range of capacities and thus limit the number of devices that can participate in training. We present Federated Averaging in Random subspaces (FAIR), which allows arbitrary compression of embedding tables based on device capacity and ensures the participation of all devices in training. FAIR uses what we call consistent and collapsible subspaces defined by hashing-based random projections to jointly train large embedding tables while using varying amounts of compression on user devices. We evaluate FAIR on Neural Collaborative Filtering tasks with multiple datasets and verify that FAIR can gather and share information from a wide range of devices with varying capacities, allowing for seamless collaboration. We prove the convergence of FAIR in the homogeneous setting with non-i.i.d data distribution. Our code is open source at {https://github.com/apd10/FLCF}

cs.LG↗

arXiv2023

In defense of parameter sharing for model-compression

When considering a model architecture, there are several ways to reduce its memory footprint. Historically, popular approaches included selecting smaller architectures and creating sparse networks through pruning. More recently, randomized parameter-sharing (RPS) methods have gained traction for model compression at start of training. In this paper, we comprehensively assess the trade-off between memory and accuracy across RPS, pruning techniques, and building smaller models. Our findings demonstrate that RPS, which is both data and model-agnostic, consistently outperforms/matches smaller models and all moderately informed pruning strategies, such as MAG, SNIP, SYNFLOW, and GRASP, across the entire compression range. This advantage becomes particularly pronounced in higher compression scenarios. Notably, even when compared to highly informed pruning techniques like Lottery Ticket Rewinding (LTR), RPS exhibits superior performance in high compression settings. This points out inherent capacity advantage that RPS enjoys over sparse models. Theoretically, we establish RPS as a superior technique in terms of memory-efficient representation when compared to pruning for linear models. This paper argues in favor of paradigm shift towards RPS based models. During our rigorous evaluation of RPS, we identified issues in the state-of-the-art RPS technique ROAST, specifically regarding stability (ROAST's sensitivity to initialization hyperparameters, often leading to divergence) and Pareto-continuity (ROAST's inability to recover the accuracy of the original model at zero compression). We provably address both of these issues. We refer to the modified RPS, which incorporates our improvements, as STABLE-RPS.

cs.LG↗

arXiv2023

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

Large language models(LLMs) have sparked a new wave of exciting AI applications. Hosting these models at scale requires significant memory resources. One crucial memory bottleneck for the deployment stems from the context window. It is commonly recognized that model weights are memory hungry; however, the size of key-value embedding stored during the generation process (KV cache) can easily surpass the model size. The enormous size of the KV cache puts constraints on the inference batch size, which is crucial for high throughput inference workload. Inspired by an interesting observation of the attention scores, we hypothesize the persistence of importance: only pivotal tokens, which had a substantial influence at one step, will significantly influence future generations. Based on our empirical verification and theoretical analysis around this hypothesis, we propose Scissorhands, a system that maintains the memory usage of the KV cache at a fixed budget without finetuning the model. In essence, Scissorhands manages the KV cache by storing the pivotal tokens with a higher probability. We validate that Scissorhands reduces the inference memory usage of the KV cache by up to 5X without compromising model quality. We further demonstrate that Scissorhands can be combined with 4-bit quantization, traditionally used to compress model weights, to achieve up to 20X compression.

cs.LG↗

arXiv2022

Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing

Advancements in deep learning are often associated with increasing model sizes. The model size dramatically affects the deployment cost and latency of deep models. For instance, models like BERT cannot be deployed on edge devices and mobiles due to their sheer size. As a result, most advances in Deep Learning are yet to reach the edge. Model compression has sought much-deserved attention in literature across natural language processing, vision, and recommendation domains. This paper proposes a model-agnostic, cache-friendly model compression approach: Random Operation Access Specific Tile (ROAST) hashing. ROAST collapses the parameters by clubbing them through a lightweight mapping. Notably, while clubbing these parameters, ROAST utilizes cache hierarchies by aligning the memory access pattern with the parameter access pattern. ROAST is up to $\sim 25 \times$ faster to train and $\sim 50 \times$ faster to infer than the popular parameter sharing method HashedNet. Additionally, ROAST introduces global weight sharing, which is empirically and theoretically superior to local weight sharing in HashedNet, and can be of independent interest in itself. With ROAST, we present the first compressed BERT, which is $100\times - 1000\times$ smaller but does not result in quality degradation. These compression levels on universal architecture like transformers are promising for the future of SOTA model deployment on resource-constrained devices like mobile and edge devices

cs.LG↗

arXiv2022

The trade-offs of model size in large recommendation models : A 10000 $\times$ compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)

Embedding tables dominate industrial-scale recommendation model sizes, using up to terabytes of memory. A popular and the largest publicly available machine learning MLPerf benchmark on recommendation data is a Deep Learning Recommendation Model (DLRM) trained on a terabyte of click-through data. It contains 100GB of embedding memory (25+Billion parameters). DLRMs, due to their sheer size and the associated volume of data, face difficulty in training, deploying for inference, and memory bottlenecks due to large embedding tables. This paper analyzes and extensively evaluates a generic parameter sharing setup (PSS) for compressing DLRM models. We show theoretical upper bounds on the learnable memory requirements for achieving $(1 \pm ε)$ approximations to the embedding table. Our bounds indicate exponentially fewer parameters suffice for good accuracy. To this end, we demonstrate a PSS DLRM reaching 10000$\times$ compression on criteo-tb without losing quality. Such a compression, however, comes with a caveat. It requires 4.5 $\times$ more iterations to reach the same saturation quality. The paper argues that this tradeoff needs more investigations as it might be significantly favorable. Leveraging the small size of the compressed model, we show a 4.3$\times$ improvement in training latency leading to similar overall training times. Thus, in the tradeoff between system advantage of a small DLRM model vs. slower convergence, we show that scales are tipped towards having a smaller DLRM model, leading to faster inference, easier deployment, and similar training times.

cs.LG↗

arXiv2022

Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\times$ Compression and 3.1$\times$ Faster Inference

Deep learning for recommendation data is one of the most pervasive and challenging AI workload in recent times. State-of-the-art recommendation models are one of the largest models matching the likes of GPT-3 and Switch Transformer. Challenges in deep learning recommendation models (DLRM) stem from learning dense embeddings for each of the categorical tokens. These embedding tables in industrial scale models can be as large as hundreds of terabytes. Such large models lead to a plethora of engineering challenges, not to mention prohibitive communication overheads, and slower training and inference times. Of these, slower inference time directly impacts user experience. Model compression for DLRM is gaining traction and the community has recently shown impressive compression results. In this paper, we present Random Offset Block Embedding Array (ROBE) as a low memory alternative to embedding tables which provide orders of magnitude reduction in memory usage while maintaining accuracy and boosting execution speed. ROBE is a simple fundamental approach in improving both cache performance and the variance of randomized hashing, which could be of independent interest in itself. We demonstrate that we can successfully train DLRM models with same accuracy while using $1000 \times$ less memory. A $1000\times$ compressed model directly results in faster inference without any engineering effort. In particular, we show that we can train DLRM model using ROBE array of size 100MB on a single GPU to achieve AUC of 0.8025 or higher as required by official MLPerf CriteoTB benchmark DLRM model of 100GB while achieving about $3.1\times$ (209\%) improvement in inference throughput.

cs.IR↗

arXiv2021

Active Sampling Count Sketch (ASCS) for Online Sparse Estimation of a Trillion Scale Covariance Matrix

Estimating and storing the covariance (or correlation) matrix of high-dimensional data is computationally challenging because both memory and computational requirements scale quadratically with the dimension. Fortunately, high-dimensional covariance matrices as observed in text, click-through, meta-genomics datasets, etc are often sparse. In this paper, we consider the problem of efficient sparse estimation of covariance matrices with possibly trillions of entries. The size of the datasets we target requires the algorithm to be online, as more than one pass over the data is prohibitive. In this paper, we propose Active Sampling Count Sketch (ASCS), an online and one-pass sketching algorithm, that recovers the large entries of the covariance matrix accurately. Count Sketch (CS), and other sub-linear compressed sensing algorithms, offer a natural solution to the problem in theory. However, vanilla CS does not work well in practice due to a low signal-to-noise ratio (SNR). At the heart of our approach is a novel active sampling strategy that increases the SNR of classical CS. We demonstrate the practicality of our algorithm with synthetic data and real-world high dimensional datasets. ASCS significantly improves over vanilla CS, demonstrating the merit of our active sampling strategy.

cs.DS↗