arXiv subjects

Peilin Zhong

Publications and source records attributed to Peilin Zhong.

At least 19 recordsLinked to original sources

arXiv2026

Memory Caching: RNNs with Growing Memory

Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plausible for retrieval tasks, it causes quadratic complexity and so has motivated recent studies to explore viable subquadratic recurrent alternatives. Despite showing promising preliminary results in diverse domains, such recurrent architectures underperform Transformers in recall-intensive tasks, often attributed to their fixed-size memory. In this paper, we introduce Memory Caching (MC), a simple yet effective technique that enhances recurrent models by caching checkpoints of their memory states (a.k.a. hidden states). Memory Caching allows the effective memory capacity of RNNs to grow with sequence length, offering a flexible trade-off that interpolates between the fixed memory (i.e., $O(L)$ complexity) of RNNs and the growing memory (i.e., $O(L^2)$ complexity) of Transformers. We propose four variants of MC, including gated aggregation and sparse selective mechanisms, and discuss their implications on both linear and deep memory modules. Our experimental results on language modeling, and long-context understanding tasks show that MC enhances the performance of recurrent models, supporting its effectiveness. The results of in-context recall tasks indicate that while Transformers achieve the best accuracy, our MC variants show competitive performance, close the gap with Transformers, and performs better than state-of-the-art recurrent models.

cs.LG↗

arXiv2025

Nested Learning: The Illusion of Deep Learning Architectures

Despite the recent progresses, particularly in developing Language Models, there are fundamental challenges and unanswered questions about how such models can continually learn/memorize, self-improve, and find effective solutions. In this paper, we present a new learning paradigm, called Nested Learning (NL), that coherently represents a machine learning model with a set of nested, multi-level, and/or parallel optimization problems, each of which with its own context flow. Through the lenses of NL, existing deep learning methods learns from data through compressing their own context flow, and in-context learning naturally emerges in large models. NL suggests a philosophy to design more expressive learning algorithms with more levels, resulting in higher-order in-context learning and potentially unlocking effective continual learning capabilities. We advocate for NL by presenting three core contributions: (1) Expressive Optimizers: We show that known gradient-based optimizers, such as Adam, SGD with Momentum, etc., are in fact associative memory modules that aim to compress the gradients' information (by gradient descent). Building on this insight, we present other more expressive optimizers with deep memory and/or more powerful learning rules; (2) Self-Modifying Learning Module: Taking advantage of NL's insights on learning algorithms, we present a sequence model that learns how to modify itself by learning its own update algorithm; and (3) Continuum Memory System: We present a new formulation for memory system that generalizes the traditional viewpoint of long/short-term memory. Combining our self-modifying sequence model with the continuum memory system, we present a continual learning module, called Hope, showing promising results in language modeling, knowledge incorporation, and few-shot generalization tasks, continual learning, and long-context reasoning tasks.

cs.LG↗

arXiv2025

MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling

State-space models (SSMs) have recently attention as an efficient alternative to computationally expensive attention-based models for sequence modeling. They rely on linear recurrences to integrate information over time, enabling fast inference, parallelizable training, and control over recurrence stability. However, traditional SSMs often suffer from limited effective memory, requiring larger state sizes for improved recall. Moreover, existing SSMs struggle to capture multi-scale dependencies, which are essential for modeling complex structures in time series, images, and natural language. This paper introduces a multi-scale SSM framework that addresses these limitations by representing sequence dynamics across multiple resolution and processing each resolution with specialized state-space dynamics. By capturing both fine-grained, high-frequency patterns and coarse, global trends, MS-SSM enhances memory efficiency and long-range modeling. We further introduce an input-dependent scale-mixer, enabling dynamic information fusion across resolutions. The proposed approach significantly improves sequence modeling, particularly in long-range and hierarchical tasks, while maintaining computational efficiency. Extensive experiments on benchmarks, including Long Range Arena, hierarchical reasoning, time series classification, and image recognition, demonstrate that MS-SSM consistently outperforms prior SSM-based models, highlighting the benefits of multi-resolution processing in state-space architectures.

cs.LG↗

arXiv2025

TNT: Improving Chunkwise Training for Test-Time Memorization

Recurrent neural networks (RNNs) with deep test-time memorization modules, such as Titans and TTT, represent a promising, linearly-scaling paradigm distinct from Transformers. While these expressive models do not yet match the peak performance of state-of-the-art Transformers, their potential has been largely untapped due to prohibitively slow training and low hardware utilization. Existing parallelization methods force a fundamental conflict governed by the chunksize hyperparameter: large chunks boost speed but degrade performance, necessitating a fixed, suboptimal compromise. To solve this challenge, we introduce TNT, a novel training paradigm that decouples training efficiency from inference performance through a two-stage process. Stage one is an efficiency-focused pre-training phase utilizing a hierarchical memory. A global module processes large, hardware-friendly chunks for long-range context, while multiple parallel local modules handle fine-grained details. Crucially, by periodically resetting local memory states, we break sequential dependencies to enable massive context parallelization. Stage two is a brief fine-tuning phase where only the local memory modules are adapted to a smaller, high-resolution chunksize, maximizing accuracy with minimal overhead. Evaluated on Titans and TTT models, TNT achieves a substantial acceleration in training speed-up to 17 times faster than the most accurate baseline configuration - while simultaneously improving model accuracy. This improvement removes a critical scalability barrier, establishing a practical foundation for developing expressive RNNs and facilitating future work to close the performance gap with Transformers.

cs.LG↗

arXiv2025

Massively Parallel Minimum Spanning Tree in General Metric Spaces

We study the minimum spanning tree (MST) problem in the massively parallel computation (MPC) model. Our focus is particularly on the *strictly sublinear* regime of MPC where the space per machine is $O(n^δ)$. Here $n$ is the number of vertices and constant $δ\in (0, 1)$ can be made arbitrarily small. The MST problem admits a simple and folklore $O(\log n)$-round algorithm in the MPC model. When the weights can be arbitrary, this matches a conditional lower bound of $Ω(\log n)$ which follows from a well-known 1vs2-Cycle conjecture. As such, much of the literature focuses on breaking the logarithmic barrier in more structured variants of the problem, such as when the vertices correspond to points in low- [ANOY14, STOC'14] or high-dimensional Euclidean spaces [JMNZ, SODA'24]. In this work, we focus more generally on metric spaces. Namely, all pairwise weights are provided and guaranteed to satisfy the triangle inequality, but are otherwise unconstrained. We show that for any $\varepsilon > 0$, a $(1+\varepsilon)$-approximate MST can be found in $O(\log \frac{1}{\varepsilon} + \log \log n)$ rounds, which is the first $o(\log n)$-round algorithm for finding any constant approximation in this setting. Other than being applicable to more general weight functions, our algorithm also slightly improves the $O(\log \log n \cdot \log \log \log n)$ round-complexity of [JMNZ24, SODA'24] and significantly improves its approximation from a large constant to $1+\varepsilon$. On the lower bound side, we prove that under the 1vs2-Cycle conjecture, $Ω(\log \frac{1}{\varepsilon})$ rounds are needed for finding a $(1+\varepsilon)$-approximate MST in general metrics. It is worth noting that while many existing lower bounds in the MPC model under the 1vs2-Cycle conjecture only hold against "component stable" algorithms, our lower bound applies to *all* algorithms.

cs.DS↗

arXiv2025

Differentially Private Clustering in Data Streams

Clustering problems (such as $k$-means and $k$-median) are fundamental unsupervised machine learning primitives, and streaming clustering algorithms have been extensively studied in the past. However, since data privacy becomes a central concern in many real-world applications, non-private clustering algorithms may not be as applicable in many scenarios. In this work, we provide the first differentially private algorithms for $k$-means and $k$-median clustering of $d$-dimensional Euclidean data points over a stream with length at most $T$ using space that is sublinear (in $T$) in the continual release setting where the algorithm is required to output a clustering at every timestep. We achieve (1) an $O(1)$-multiplicative approximation with $\tilde{O}(k^{1.5} \cdot poly(d,\log(T)))$ space and $poly(k,d,\log(T))$ additive error, or (2) a $(1+γ)$-multiplicative approximation with $\tilde{O}_γ(poly(k,2^{O_γ(d)},\log(T)))$ space for any $γ>0$, and the additive error is $poly(k,2^{O_γ(d)},\log(T))$. Our main technical contribution is a differentially private clustering framework for data streams which only requires an offline DP coreset or clustering algorithm as a blackbox.

cs.DS↗

arXiv2025

Differentially Private Synthetic Data Release for Topics API Outputs

The analysis of the privacy properties of Privacy-Preserving Ads APIs is an area of research that has received strong interest from academics, industry, and regulators. Despite this interest, the empirical study of these methods is hindered by the lack of publicly available data. Reliable empirical analysis of the privacy properties of an API, in fact, requires access to a dataset consisting of realistic API outputs; however, privacy concerns prevent the general release of such data to the public. In this work, we develop a novel methodology to construct synthetic API outputs that are simultaneously realistic enough to enable accurate study and provide strong privacy protections. We focus on one Privacy-Preserving Ads APIs: the Topics API, part of Google Chrome's Privacy Sandbox. We developed a methodology to generate a differentially-private dataset that closely matches the re-identification risk properties of the real Topics API data. The use of differential privacy provides strong theoretical bounds on the leakage of private user information from this release. Our methodology is based on first computing a large number of differentially-private statistics describing how output API traces evolve over time. Then, we design a parameterized distribution over sequences of API traces and optimize its parameters so that they closely match the statistics obtained. Finally, we create the synthetic data by drawing from this distribution. Our work is complemented by an open-source release of the anonymized dataset obtained by this methodology. We hope this will enable external researchers to analyze the API in-depth and replicate prior and future work on a realistic large-scale dataset. We believe that this work will contribute to fostering transparency regarding the privacy properties of Privacy-Preserving Ads APIs.

cs.CR↗

arXiv2025

PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts

Modern foundation models are trained on diverse datasets to enhance generalization across tasks and domains A central challenge in this process is determining how to effectively mix and sample data from multiple sources This naturally leads to a multitask learning (MTL) perspective While prior work in MTL has emphasized mitigating gradient conflicts we observe that largescale pretraining scenariossuch as multilingual or multidomain trainingoften exhibit little to no gradient conflict Motivated by this observation we propose PiKE (Positive gradient interaction-based K-task weights Estimator) an adaptive data mixing algorithm that dynamically adjusts sampling weights during training PiKE exploits nonconflicting gradient interactions to minimize a neartight upper bound on the average loss decrease at each step while incurring negligible computational overhead We provide theoretical convergence guarantees and show that PiKE outperforms static and nonadaptive mixing baselines Furthermore we extend PiKE to promote balanced learning across tasks Extensive experiments on largescale language model pretraining confirm that PiKE achieves faster convergence and improved downstream performance compared to existing approaches

cs.LG↗

arXiv2025

Differentially Private Space-Efficient Algorithms for Counting Distinct Elements in the Turnstile Model

The turnstile continual release model of differential privacy captures scenarios where a privacy-preserving real-time analysis is sought for a dataset evolving through additions and deletions. In typical applications of real-time data analysis, both the length of the stream $T$ and the size of the universe $|U|$ from which data come can be extremely large. This motivates the study of private algorithms in the turnstile setting using space sublinear in both $T$ and $|U|$. In this paper, we give the first sublinear space differentially private algorithms for the fundamental problem of counting distinct elements in the turnstile streaming model. Our algorithm achieves, on arbitrary streams, $\tilde{O}_η(T^{1/3})$ space and additive error, and a $(1+η)$-relative approximation for all $η\in (0,1)$. Our result significantly improves upon the space requirements of the state-of-the-art algorithms for this problem, which is linear, approaching the known $Ω(T^{1/4})$ additive error lower bound for arbitrary streams. Moreover, when a bound $W$ on the number of times an item appears in the stream is known, our algorithm provides $\tilde{O}_η(\sqrt{W})$ additive error, using $\tilde{O}_η(\sqrt{W})$ space. This additive error asymptotically matches that of prior work which required instead linear space. Our results address an open question posed by [Jain, Kalemaj, Raskhodnikova, Sivakumar, Smith, Neurips23] about designing low-memory mechanisms for this problem. We complement these results with a space lower bound for this problem, which shows that any algorithm that uses similar techniques must use space $\tildeΩ(T^{1/3})$ on arbitrary streams.

cs.DS↗

arXiv2025

ATLAS: Learning to Optimally Memorize the Context at Test Time

Transformers have been established as the most popular backbones in sequence modeling, mainly due to their effectiveness in in-context retrieval tasks and the ability to learn at scale. Their quadratic memory and time complexity, however, bound their applicability in longer sequences and so has motivated researchers to explore effective alternative architectures such as modern recurrent neural networks (a.k.a long-term recurrent memory module). Despite their recent success in diverse downstream tasks, they struggle in tasks that requires long context understanding and extrapolation to longer sequences. We observe that these shortcomings come from three disjoint aspects in their design: (1) limited memory capacity that is bounded by the architecture of memory and feature mapping of the input; (2) online nature of update, i.e., optimizing the memory only with respect to the last input; and (3) less expressive management of their fixed-size memory. To enhance all these three aspects, we present ATLAS, a long-term memory module with high capacity that learns to memorize the context by optimizing the memory based on the current and past tokens, overcoming the online nature of long-term memory models. Building on this insight, we present a new family of Transformer-like architectures, called DeepTransformers, that are strict generalizations of the original Transformer architecture. Our experimental results on language modeling, common-sense reasoning, recall-intensive, and long-context understanding tasks show that ATLAS surpasses the performance of Transformers and recent linear recurrent models. ATLAS further improves the long context performance of Titans, achieving +80\% accuracy in 10M context length of BABILong benchmark.

cs.CL↗

arXiv2025

Retraining with Predicted Hard Labels Provably Increases Model Accuracy

The performance of a model trained with noisy labels is often improved by simply \textit{retraining} the model with its \textit{own predicted hard labels} (i.e., 1/0 labels). Yet, a detailed theoretical characterization of this phenomenon is lacking. In this paper, we theoretically analyze retraining in a linearly separable binary classification setting with randomly corrupted labels given to us and prove that retraining can improve the population accuracy obtained by initially training with the given (noisy) labels. To the best of our knowledge, this is the first such theoretical result. Retraining finds application in improving training with local label differential privacy (DP) which involves training with noisy labels. We empirically show that retraining selectively on the samples for which the predicted label matches the given label significantly improves label DP training at no extra privacy cost; we call this consensus-based retraining. As an example, when training ResNet-18 on CIFAR-100 with $ε=3$ label DP, we obtain more than 6% improvement in accuracy with consensus-based retraining.

cs.LG↗

arXiv2025

Maximum Coverage in Turnstile Streams with Applications to Fingerprinting Measures

In the maximum coverage problem we are given $d$ subsets from a universe $[n]$, and the goal is to output $k$ subsets such that their union covers the largest possible number of distinct items. We present the first algorithm for maximum coverage in the turnstile streaming model, where updates which insert or delete an item from a subset come one-by-one. Notably our algorithm only uses $poly\log n$ update time. We also present turnstile streaming algorithms for targeted and general fingerprinting for risk management where the goal is to determine which features pose the greatest re-identification risk in a dataset. As part of our work, we give a result of independent interest: an algorithm to estimate the complement of the $p^{\text{th}}$ frequency moment of a vector for $p \geq 2$. Empirical evaluation confirms the practicality of our fingerprinting algorithms demonstrating a speedup of up to $210$x over prior work.

cs.DS↗

arXiv2025

It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization

Designing efficient and effective architectural backbones has been in the core of research efforts to enhance the capability of foundation models. Inspired by the human cognitive phenomenon of attentional bias-the natural tendency to prioritize certain events or stimuli-we reconceptualize neural architectures, including Transformers, Titans, and modern linear recurrent neural networks as associative memory modules that learn a mapping of keys and values using an internal objective, referred to as attentional bias. Surprisingly, we observed that most existing sequence models leverage either (1) dot-product similarity, or (2) L2 regression objectives as their attentional bias. Going beyond these objectives, we present a set of alternative attentional bias configurations along with their effective approximations to stabilize their training procedure. We then reinterpret forgetting mechanisms in modern deep learning architectures as a form of retention regularization, providing a novel set of forget gates for sequence models. Building upon these insights, we present Miras, a general framework to design deep learning architectures based on four choices of: (i) associative memory architecture, (ii) attentional bias objective, (iii) retention gate, and (iv) memory learning algorithm. We present three novel sequence models-Moneta, Yaad, and Memora-that go beyond the power of existing linear RNNs while maintaining a fast parallelizable training process. Our experiments show different design choices in Miras yield models with varying strengths. For example, certain instances of Miras achieve exceptional performance in special tasks such as language modeling, commonsense reasoning, and recall intensive tasks, even outperforming Transformers and other modern linear recurrent models.

cs.LG↗

arXiv2024

Titans: Learning to Memorize at Test Time

Over more than a decade there has been an extensive research effort on how to effectively utilize recurrent models and attention. While recurrent models aim to compress the data into a fixed-size memory (called hidden state), attention allows attending to the entire context window, capturing the direct dependencies of all tokens. This more accurate modeling of dependencies, however, comes with a quadratic cost, limiting the model to a fixed-length context. We present a new neural long-term memory module that learns to memorize historical context and helps attention to attend to the current context while utilizing long past information. We show that this neural memory has the advantage of fast parallelizable training while maintaining a fast inference. From a memory perspective, we argue that attention due to its limited context but accurate dependency modeling performs as a short-term memory, while neural memory due to its ability to memorize the data, acts as a long-term, more persistent, memory. Based on these two modules, we introduce a new family of architectures, called Titans, and present three variants to address how one can effectively incorporate memory into this architecture. Our experimental results on language modeling, common-sense reasoning, genomics, and time series tasks show that Titans are more effective than Transformers and recent modern linear recurrent models. They further can effectively scale to larger than 2M context window size with higher accuracy in needle-in-haystack tasks compared to baselines.

cs.LG↗

arXiv2024

Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models

Fine-tuning language models (LMs) with the Adam optimizer often demands excessive memory, limiting accessibility. The "in-place" version of Stochastic Gradient Descent (IP-SGD) and Memory-Efficient Zeroth-order Optimizer (MeZO) have been proposed to address this. However, IP-SGD still requires substantial memory, and MeZO suffers from slow convergence and degraded final performance due to its zeroth-order nature. This paper introduces Addax, a novel method that improves both memory efficiency and performance of IP-SGD by integrating it with MeZO. Specifically, Addax computes zeroth- or first-order gradients of data points in the minibatch based on their memory consumption, combining these gradient estimates to update directions. By computing zeroth-order gradients for data points that require more memory and first-order gradients for others, Addax overcomes the slow convergence of MeZO and the excessive memory requirement of IP-SGD. Additionally, the zeroth-order gradient acts as a regularizer for the first-order gradient, further enhancing the model's final performance. Theoretically, we establish the convergence of Addax under mild assumptions, demonstrating faster convergence and less restrictive hyper-parameter choices than MeZO. Our experiments with diverse LMs and tasks show that Addax consistently outperforms MeZO regarding accuracy and convergence speed while having a comparable memory footprint. When fine-tuning OPT-13B with one A100 GPU, on average, Addax outperforms MeZO in accuracy/F1 score by 14% and runs 15x faster while using memory similar to MeZO. In our experiments on the larger OPT-30B model, on average, Addax outperforms MeZO in terms of accuracy/F1 score by >16 and runs 30x faster on a single H100 GPU. Moreover, Addax surpasses the performance of standard fine-tuning approaches, such as IP-SGD and Adam, in most tasks with significantly less memory requirement.

cs.LG↗

arXiv2024

Perturb-and-Project: Differentially Private Similarities and Marginals

We revisit the input perturbations framework for differential privacy where noise is added to the input $A\in \mathcal{S}$ and the result is then projected back to the space of admissible datasets $\mathcal{S}$. Through this framework, we first design novel efficient algorithms to privately release pair-wise cosine similarities. Second, we derive a novel algorithm to compute $k$-way marginal queries over $n$ features. Prior work could achieve comparable guarantees only for $k$ even. Furthermore, we extend our results to $t$-sparse datasets, where our efficient algorithms yields novel, stronger guarantees whenever $t\le n^{5/6}/\log n\,.$ Finally, we provide a theoretical perspective on why \textit{fast} input perturbation algorithms works well in practice. The key technical ingredients behind our results are tight sum-of-squares certificates upper bounding the Gaussian complexity of sets of solutions.

cs.LG↗

arXiv2024

High-Dimensional Geometric Streaming for Nearly Low Rank Data

We study streaming algorithms for the $\ell_p$ subspace approximation problem. Given points $a_1, \ldots, a_n$ as an insertion-only stream and a rank parameter $k$, the $\ell_p$ subspace approximation problem is to find a $k$-dimensional subspace $V$ such that $(\sum_{i=1}^n d(a_i, V)^p)^{1/p}$ is minimized, where $d(a, V)$ denotes the Euclidean distance between $a$ and $V$ defined as $\min_{v \in V}\|{a - v}\|_{\infty}$. When $p = \infty$, we need to find a subspace $V$ that minimizes $\max_i d(a_i, V)$. For $\ell_{\infty}$ subspace approximation, we give a deterministic strong coreset construction algorithm and show that it can be used to compute a $\text{poly}(k, \log n)$ approximate solution. We show that the distortion obtained by our coreset is nearly tight for any sublinear space algorithm. For $\ell_p$ subspace approximation, we show that suitably scaling the points and then using our $\ell_{\infty}$ coreset construction, we can compute a $\text{poly}(k, \log n)$ approximation. Our algorithms are easy to implement and run very fast on large datasets. We also use our strong coreset construction to improve the results in a recent work of Woodruff and Yasuda (FOCS 2022) which gives streaming algorithms for high-dimensional geometric problems such as width estimation, convex hull estimation, and volume estimation.

cs.DS↗

arXiv2024

Optimal Communication for Classic Functions in the Coordinator Model and Beyond

In the coordinator model of communication with $s$ servers, given an arbitrary non-negative function $f$, we study the problem of approximating the sum $\sum_{i \in [n]}f(x_i)$ up to a $1 \pm \varepsilon$ factor. Here the vector $x \in R^n$ is defined to be $x = x(1) + \cdots + x(s)$, where $x(j) \ge 0$ denotes the non-negative vector held by the $j$-th server. A special case of the problem is when $f(x) = x^k$ which corresponds to the well-studied problem of $F_k$ moment estimation in the distributed communication model. We introduce a new parameter $c_f[s]$ which captures the communication complexity of approximating $\sum_{i\in [n]} f(x_i)$ and for a broad class of functions $f$ which includes $f(x) = x^k$ for $k \ge 2$ and other robust functions such as the Huber loss function, we give a two round protocol that uses total communication $c_f[s]/\varepsilon^2$ bits, up to polylogarithmic factors. For this broad class of functions, our result improves upon the communication bounds achieved by Kannan, Vempala, and Woodruff (COLT 2014) and Woodruff and Zhang (STOC 2012), obtaining the optimal communication up to polylogarithmic factors in the minimum number of rounds. We show that our protocol can also be used for approximating higher-order correlations. Apart from the coordinator model, algorithms for other graph topologies in which each node is a server have been extensively studied. We argue that directly lifting protocols leads to inefficient algorithms. Hence, a natural question is the problems that can be efficiently solved in general graph topologies. We give communication efficient protocols in the so-called personalized CONGEST model for solving linear regression and low rank approximation by designing composable sketches. Our sketch construction may be of independent interest and can implement any importance sampling procedure that has a monotonicity property.

cs.DS↗