English
Related papers

Related papers: Convergence of Two-Layer Regression with Nonlinear…

200 papers

Transformer architectures have achieved remarkable success in various domains. While efficient alternatives to Softmax Attention have been widely studied, the search for more expressive mechanisms grounded in theoretical insight-even at…

Machine Learning · Computer Science 2025-10-03 Yifei Zuo , Yutong Yin , Zhichen Zeng , Ang Li , Banghua Zhu , Zhaoran Wang

In this paper, we revisit the large-scale constrained linear regression problem and propose faster methods based on some recent developments in sketching and optimization. Our algorithms combine (accelerated) mini-batch SGD with a new…

Machine Learning · Computer Science 2018-02-12 Di Wang , Jinhui Xu

A current strand of research in high-dimensional statistics deals with robustifying the available methodology with respect to deviations from the pervasive light-tail assumptions. In this paper we consider a linear mean regression model…

Statistics Theory · Mathematics 2025-02-06 Philipp Hermann , Hajo Holzmann

We propose sparsemax, a new activation function similar to the traditional softmax, but able to output sparse probabilities. After deriving its properties, we show how its Jacobian can be efficiently computed, enabling its use in a network…

Computation and Language · Computer Science 2016-02-09 André F. T. Martins , Ramón Fernandez Astudillo

Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness. The optimization objective driving weight decay is a sum of losses plus a term proportional…

Machine Learning · Computer Science 2023-07-07 Liu Yang , Jifan Zhang , Joseph Shenouda , Dimitris Papailiopoulos , Kangwook Lee , Robert D. Nowak

Instruction-fine-tuned large language models (LLMs) under 14B parameters continue to underperform on natural language understanding (NLU) tasks, often trailing smaller models like BERT-base on benchmarks such as GLUE and SuperGLUE.…

Computation and Language · Computer Science 2025-09-29 Bokai Hu , Sai Ashish Somayajula , Xin Pan , Pengtao Xie

In this note, we demonstrate a first-of-its-kind provable convergence of SGD to the global minima of appropriately regularized logistic empirical risk of depth $2$ nets -- for arbitrary data and with any number of gates with adequately…

Machine Learning · Computer Science 2024-03-19 Pulkit Gopalani , Samyak Jha , Anirbit Mukherjee

The task of approximating an arbitrary convex function arises in several learning problems such as convex regression, learning with a difference of convex (DC) functions, and learning Bregman or $f$-divergences. In this paper, we develop…

Self-attention is often viewed as probabilistic query-key lookup, motivating designs that preserve normalized attention scores and fixed positional semantics. We advocate a simpler and more unified perspective: an autoregressive attention…

Machine Learning · Computer Science 2026-02-16 Jiecheng Lu , Shihao Yang

Recent work has revealed a link between self-attention mechanisms in transformers and test-time kernel regression via the Nadaraya-Watson estimator, with standard softmax attention corresponding to a Gaussian kernel. However, a…

Machine Learning · Computer Science 2026-05-11 Saul Santos , Nuno Gonçalves , Daniel C. McNamee , Marcos Treviso , André F. T Martins

Sparsification of neural networks is one of the effective complexity reduction methods to improve efficiency and generalizability. We consider the problem of learning a one hidden layer convolutional neural network with ReLU activation…

Optimization and Control · Mathematics 2020-02-26 Thu Dinh , Jack Xin

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Computation and Language · Computer Science 2025-06-12 Yuxin Jiang

Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become…

Computation and Language · Computer Science 2025-02-06 Rhea Sanjay Sukthanker , Benedikt Staffler , Frank Hutter , Aaron Klein

We prove exponential expressivity with stable ReLU Neural Networks (ReLU NNs) in $H^1(\Omega)$ for weighted analytic function classes in certain polytopal domains $\Omega$, in space dimension $d=2,3$. Functions in these classes are locally…

Numerical Analysis · Mathematics 2023-11-27 Carlo Marcati , Joost A. A. Opschoor , Philipp C. Petersen , Christoph Schwab

We investigate the complexity of training a two-layer ReLU neural network with weight decay regularization. Previous research has shown that the optimal solution of this problem can be found by solving a standard cone-constrained convex…

Machine Learning · Computer Science 2023-11-21 Yifei Wang , Mert Pilanci

The non-convexity of the artificial neural network (ANN) training landscape brings inherent optimization difficulties. While the traditional back-propagation stochastic gradient descent (SGD) algorithm and its variants are effective in…

Machine Learning · Computer Science 2025-06-18 Yatong Bai , Tanmay Gautam , Somayeh Sojoudi

We propose a communication and computation efficient second-order method for distributed optimization. For each iteration, our method only requires $\mathcal{O}(d)$ communication complexity, where $d$ is the problem dimension. We also…

Optimization and Control · Mathematics 2023-05-30 Chengchang Liu , Lesi Chen , Luo Luo , John C. S. Lui

We consider a stochastic version of the proximal point algorithm for optimization problems posed on a Hilbert space. A typical application of this is supervised learning. While the method is not new, it has not been extensively analyzed in…

Optimization and Control · Mathematics 2021-09-28 Monika Eisenmann , Tony Stillfjord , Måns Williamson

Recent advances in adversarial attacks and Wasserstein GANs have advocated for use of neural networks with restricted Lipschitz constants. Motivated by these observations, we study the recently introduced GroupSort neural networks, with…

Machine Learning · Statistics 2021-02-09 Ugo Tanielian , Maxime Sangnier , Gerard Biau

We study the approximation of the median of $d$ inputs using ReLU neural networks. We present depth-width tradeoffs under several settings, culminating in a constant-depth, linear-width construction that achieves exponentially small…

Machine Learning · Computer Science 2026-02-10 Abhigyan Dutta , Itay Safran , Paul Valiant