arXiv subjects

Paras Jain

Publications and source records attributed to Paras Jain.

15 recordsLinked to original sources

arXiv2026

Evaluating Human and Machine Confidence in Phishing Email Detection: A Comparative Study

Identifying deceptive content like phishing emails demands sophisticated cognitive processes that combine pattern recognition, confidence assessment, and contextual analysis. This research examines how human cognition and machine learning models work together to distinguish phishing emails from legitimate ones. We employed three interpretable algorithms Logistic Regression, Decision Trees, and Random Forests training them on both TF-IDF features and semantic embeddings, then compared their predictions against human evaluations that captured confidence ratings and linguistic observations. Our results show that machine learning models provide good accuracy rates, but their confidence levels vary significantly. Human evaluators, on the other hand, use a greater variety of language signs and retain more consistent confidence. We also found that while language proficiency has minimal effect on detection performance, aging does. These findings offer helpful direction for creating transparent AI systems that complement human cognitive functions, ultimately improving human-AI cooperation in challenging content analysis tasks.

cs.AI↗

arXiv2023

An integrative phenotype-structured partial differential equation model for the population dynamics of epithelial-mesenchymal transition

Phenotypic heterogeneity along the epithelial-mesenchymal (E-M) axis contributes to cancer metastasis and drug resistance. Recent experimental efforts have collated detailed time-course data on the emergence and dynamics of E-M heterogeneity in a cell population. However, it remains unclear how different possible processes interplay in shaping the dynamics of E-M heterogeneity: a) intracellular regulatory interaction among biomolecules, b) cell division and death, and c) stochastic cell-state transition (biochemical reaction noise and asymmetric cell division). Here, we propose a Cell Population Balance (Partial Differential Equation (PDE)) based model that captures the dynamics of cell population density along the E-M phenotypic axis due to abovementioned multi-scale cellular processes. We demonstrate how population distribution resulting from intracellular regulatory networks driving cell-state transition gets impacted by stochastic fluctuations in E-M regulatory biomolecules, differences in growth rates among cell subpopulations, and initial population distribution. Further, we reveal that a linear dependence of the cell growth rate on the population heterogeneity is sufficient to recapitulate the faster in vivo growth of orthotopic injected heterogeneous E-M subclones reported before experimentally. Overall, our model contributes to the combined understanding of intracellular and cell-population levels dynamics in the emergence of E-M heterogeneity in a cell population.

math.AP↗

arXiv2022

Skyplane: Optimizing Transfer Cost and Throughput Using Cloud-Aware Overlays

Cloud applications are increasingly distributing data across multiple regions and cloud providers. Unfortunately, wide-area bulk data transfers are often slow, bottlenecking applications. We demonstrate that it is possible to significantly improve inter-region cloud bulk transfer throughput by adapting network overlays to the cloud setting -- that is, by routing data through indirect paths at the application layer. However, directly applying network overlays in this setting can result in unacceptable increases in cloud egress prices. We present Skyplane, a system for bulk data transfer between cloud object stores that uses cloud-aware network overlays to optimally navigate the trade-off between price and performance. Skyplane's planner uses mixed-integer linear programming to determine the optimal overlay path and resource allocation for data transfer, subject to user-provided constraints on price or performance. Skyplane outperforms public cloud transfer services by up to $4.6\times$ for transfers within one cloud and by up to $5.0\times$ across clouds.

cs.NI↗

arXiv2022

POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging

Fine-tuning models on edge devices like mobile phones would enable privacy-preserving personalization over sensitive data. However, edge training has historically been limited to relatively small models with simple architectures because training is both memory and energy intensive. We present POET, an algorithm to enable training large neural networks on memory-scarce battery-operated edge devices. POET jointly optimizes the integrated search search spaces of rematerialization and paging, two algorithms to reduce the memory consumption of backpropagation. Given a memory budget and a run-time constraint, we formulate a mixed-integer linear program (MILP) for energy-optimal training. Our approach enables training significantly larger models on embedded devices while reducing energy consumption while not modifying mathematical correctness of backpropagation. We demonstrate that it is possible to fine-tune both ResNet-18 and BERT within the memory constraints of a Cortex-M class embedded device while outperforming current edge training methods in energy efficiency. POET is an open-source project available at https://github.com/ShishirPatil/poet

cs.LG↗

arXiv2022

Representing Long-Range Context for Graph Neural Networks with Global Attention

Graph neural networks are powerful architectures for structured datasets. However, current methods struggle to represent long-range dependencies. Scaling the depth or width of GNNs is insufficient to broaden receptive fields as larger GNNs encounter optimization instabilities such as vanishing gradients and representation oversmoothing, while pooling-based approaches have yet to become as universally useful as in computer vision. In this work, we propose the use of Transformer-based self-attention to learn long-range pairwise relationships, with a novel "readout" mechanism to obtain a global graph embedding. Inspired by recent computer vision results that find position-invariant attention performant in learning long-range relationships, our method, which we call GraphTrans, applies a permutation-invariant Transformer module after a standard GNN module. This simple architecture leads to state-of-the-art results on several graph classification tasks, outperforming methods that explicitly encode graph structure. Our results suggest that purely-learning-based approaches without graph structure may be suitable for learning high-level, long-range relationships on graphs. Code for GraphTrans is available at https://github.com/ucbrise/graphtrans.

cs.LG↗

arXiv2022

Contrastive Code Representation Learning

Recent work learns contextual representations of source code by reconstructing tokens from their context. For downstream semantic understanding tasks like summarizing code in English, these representations should ideally capture program functionality. However, we show that the popular reconstruction-based BERT model is sensitive to source code edits, even when the edits preserve semantics. We propose ContraCode: a contrastive pre-training task that learns code functionality, not form. ContraCode pre-trains a neural network to identify functionally similar variants of a program among many non-equivalent distractors. We scalably generate these variants using an automated source-to-source compiler as a form of data augmentation. Contrastive pre-training improves JavaScript summarization and TypeScript type inference accuracy by 2% to 13%. We also propose a new zero-shot JavaScript code clone detection dataset, showing that ContraCode is both more robust and semantically meaningful. On it, we outperform RoBERTa by 39% AUROC in an adversarial setting and up to 5% on natural code.

cs.LG↗

arXiv2021

Grounded Graph Decoding Improves Compositional Generalization in Question Answering

Question answering models struggle to generalize to novel compositions of training patterns, such to longer sequences or more complex test structures. Current end-to-end models learn a flat input embedding which can lose input syntax context. Prior approaches improve generalization by learning permutation invariant models, but these methods do not scale to more complex train-test splits. We propose Grounded Graph Decoding, a method to improve compositional generalization of language representations by grounding structured predictions with an attention mechanism. Grounding enables the model to retain syntax information from the input in thereby significantly improving generalization over complex inputs. By predicting a structured graph containing conjunctions of query clauses, we learn a group invariant representation without making assumptions on the target domain. Our model significantly outperforms state-of-the-art baselines on the Compositional Freebase Questions (CFQ) dataset, a challenging benchmark for compositional generalization in question answering. Moreover, we effectively solve the MCD1 split with 98% accuracy.

cs.CL↗

arXiv2021

Accelerating Quadratic Optimization with Reinforcement Learning

First-order methods for quadratic optimization such as OSQP are widely used for large-scale machine learning and embedded optimal control, where many related problems must be rapidly solved. These methods face two persistent challenges: manual hyperparameter tuning and convergence time to high-accuracy solutions. To address these, we explore how Reinforcement Learning (RL) can learn a policy to tune parameters to accelerate convergence. In experiments with well-known QP benchmarks we find that our RL policy, RLQP, significantly outperforms state-of-the-art QP solvers by up to 3x. RLQP generalizes surprisingly well to previously unseen problems with varying dimension and structure from different applications, including the QPLIB, Netlib LP and Maros-Meszaros problems. Code for RLQP is available at https://github.com/berkeleyautomation/rlqp.

cs.LG↗

arXiv2020

Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization

We formalize the problem of trading-off DNN training time and memory requirements as the tensor rematerialization optimization problem, a generalization of prior checkpointing strategies. We introduce Checkmate, a system that solves for optimal rematerialization schedules in reasonable times (under an hour) using off-the-shelf MILP solvers or near-optimal schedules with an approximation algorithm, then uses these schedules to accelerate millions of training iterations. Our method scales to complex, realistic architectures and is hardware-aware through the use of accelerator-specific, profile-based cost models. In addition to reducing training cost, Checkmate enables real-world networks to be trained with up to 5.1x larger input sizes. Checkmate is an open-source project, available at https://github.com/parasj/checkmate.

cs.LG↗

arXiv2019

Revec: Program Rejuvenation through Revectorization

Modern microprocessors are equipped with Single Instruction Multiple Data (SIMD) or vector instructions which expose data level parallelism at a fine granularity. Programmers exploit this parallelism by using low-level vector intrinsics in their code. However, once programs are written using vector intrinsics of a specific instruction set, the code becomes non-portable. Modern compilers are unable to analyze and retarget the code to newer vector instruction sets. Hence, programmers have to manually rewrite the same code using vector intrinsics of a newer generation to exploit higher data widths and capabilities of new instruction sets. This process is tedious, error-prone and requires maintaining multiple code bases. We propose Revec, a compiler optimization pass which revectorizes already vectorized code, by retargeting it to use vector instructions of newer generations. The transformation is transparent, happening at the compiler intermediate representation level, and enables performance portability of hand-vectorized code. Revec can achieve performance improvements in real-world performance critical kernels. In particular, Revec achieves geometric mean speedups of 1.160$\times$ and 1.430$\times$ on fast integer unpacking kernels, and speedups of 1.145$\times$ and 1.195$\times$ on hand-vectorized x265 media codec kernels when retargeting their SSE-series implementations to use AVX2 and AVX-512 vector instructions respectively. We also extensively test Revec's impact on 216 intrinsic-rich implementations of image processing and stencil kernels relative to hand-retargeting.

cs.PL↗

arXiv2019

The OoO VLIW JIT Compiler for GPU Inference

Current trends in Machine Learning~(ML) inference on hardware accelerated devices (e.g., GPUs, TPUs) point to alarmingly low utilization. As ML inference is increasingly time-bounded by tight latency SLOs, increasing data parallelism is not an option. The need for better efficiency motivates GPU multiplexing. Furthermore, existing GPU programming abstractions force programmers to micro-manage GPU resources in an early-binding, context-free fashion. We propose a VLIW-inspired Out-of-Order (OoO) Just-in-Time (JIT) compiler that coalesces and reorders execution kernels at runtime for throughput-optimal device utilization while satisfying latency SLOs. We quantify the inefficiencies of space-only and time-only multiplexing alternatives and demonstrate an achievable 7.7x opportunity gap through spatial coalescing.

cs.DC↗

arXiv2018

Dynamic Space-Time Scheduling for GPU Inference

Serving deep neural networks in latency critical interactive settings often requires GPU acceleration. However, the small batch sizes typical in online inference results in poor GPU utilization, a potential performance gap which GPU resource sharing can address. In this paper, we explore several techniques to leverage both temporal and spatial multiplexing to improve GPU utilization for deep learning inference workloads. We evaluate the performance trade-offs of each approach with respect to resource-efficiency, latency predictability, and isolation when compared with conventional batched inference. Our experimental analysis suggests up to a 5x potential for improved utilization through the exploration of more advanced spatial and temporal multiplexing strategies. Our preliminary prototype of a dynamic space-time scheduler demonstrates a 3.23x floating-point throughput increase over space-only multiplexing and a 7.73x increase over time-only multiplexing for convolutions, while also providing better isolation and latency predictability.

cs.DC↗

arXiv2018

DSCnet: Replicating Lidar Point Clouds with Deep Sensor Cloning

Convolutional neural networks (CNNs) have become increasingly popular for solving a variety of computer vision tasks, ranging from image classification to image segmentation. Recently, autonomous vehicles have created a demand for depth information, which is often obtained using hardware sensors such as Light detection and ranging (LIDAR). Although it can provide precise distance measurements, most LIDARs are still far too expensive to sell in mass-produced consumer vehicles, which has motivated methods to generate depth information from commodity automotive sensors like cameras. In this paper, we propose an approach called Deep Sensor Cloning (DSC). The idea is to use Convolutional Neural Networks in conjunction with inexpensive sensors to replicate the 3D point-clouds that are created by expensive LIDARs. To accomplish this, we develop a new dataset (DSDepth) and a new family of CNN architectures (DSCnets). While previous tasks such as KITTI depth prediction use an interpolated RGB-D images as ground-truth for training, we instead use DSCnets to directly predict LIDAR point-clouds. When we compare the output of our models to a $75,000 LIDAR, we find that our most accurate DSCnet achieves a relative error of 5.77% using a single camera and 4.69% using stereo cameras.

cs.CV↗

arXiv2017

Scalable Architecture for Anomaly Detection and Visualization in Power Generating Assets

Power-generating assets (e.g., jet engines, gas turbines) are often instrumented with tens to hundreds of sensors for monitoring physical and performance degradation. Anomaly detection algorithms highlight deviations from predetermined benchmarks with the goal of detecting incipient faults. We are developing an integrated system to address three key challenges within analyzing sensor data from power-generating assets: (1) difficulty in ingesting and analyzing data from large numbers of machines; (2) prevalence of false alarms generated by anomaly detection algorithms resulting in unnecessary downtime and maintenance; and (3) lack of an integrated visualization that helps users understand and explore the flagged anomalies and relevant sensor context in the energy domain. We present preliminary results and our key findings in addressing these challenges. Our system's scalable event ingestion framework, based on OpenTSDB, ingests nearly 400,000 sensor data samples per seconds using a 30 machine cluster. To reduce false alarm rates, we leverage the False Discovery Rate (FDR) algorithm which significantly reduces the number of false alarms. Our visualization tool presents the anomalies and associated content flagged by the FDR algorithm to inform users and practitioners in their decision making process. We believe our integrated platform will help reduce maintenance costs significantly while increasing asset lifespan. We are working to extend our system on multiple fronts, such as scaling to more data and more compute nodes (70 in total).

cs.DC↗

arXiv2015

Spotting Suspicious Reviews via (Quasi-)clique Extraction

How to tell if a review is real or fake? What does the underworld of fraudulent reviewing look like? Detecting suspicious reviews has become a major issue for many online services. We propose the use of a clique-finding approach to discover well-organized suspicious reviewers. From a Yelp dataset with over one million reviews, we construct multiple Reviewer Similarity graphs to link users that have unusually similar behavior: two reviewers are connected in the graph if they have reviewed the same set of venues within a few days. From these graphs, our algorithms extracted many large cliques and quasi-cliques, the largest one containing a striking 11 users who coordinated their review activities in identical ways. Among the detected cliques, a large portion contain Yelp Scouts who are paid by Yelp to review venues in new areas. Our work sheds light on their little-known operation.

cs.SI↗