English
Related papers

Related papers: Convergence of Gradient Descent on Separable Data

200 papers

Stochastic-approximation gradient methods are attractive for large-scale convex optimization because they offer inexpensive iterations. They are especially popular in data-fitting and machine-learning applications where the data arrives in…

Optimization and Control · Mathematics 2014-01-09 Michael P. Friedlander , Gabriel Goh

The Kullback-Leibler (KL) divergence plays a central role in probabilistic machine learning, where it commonly serves as the canonical loss function. Optimization in such settings is often performed over the probability simplex, where the…

Machine Learning · Computer Science 2025-07-31 Adwait Datar , Nihat Ay

First-order optimization methods tend to inherently favor certain solutions over others when minimizing an underdetermined training objective that has multiple global optima. This phenomenon, known as implicit bias, plays a critical role in…

Machine Learning · Computer Science 2024-04-09 Guanghui Wang , Zihao Hu , Claudio Gentile , Vidya Muthukumar , Jacob Abernethy

Stochastic gradient descent is a canonical tool for addressing stochastic optimization problems, and forms the bedrock of modern machine learning and statistics. In this work, we seek to balance the fact that attenuating step-size is…

Signal Processing · Electrical Eng. & Systems 2020-07-10 Zhan Gao , Alec Koppel , Alejandro Ribeiro

Recent studies have shown that heavy tails can emerge in stochastic optimization and that the heaviness of the tails have links to the generalization error. While these studies have shed light on interesting aspects of the generalization…

Machine Learning · Statistics 2023-02-14 Anant Raj , Melih Barsbey , Mert Gürbüzbalaban , Lingjiong Zhu , Umut Şimşekli

In recent years, various notions of capacity and complexity have been proposed for characterizing the generalization properties of stochastic gradient descent (SGD) in deep learning. Some of the popular notions that correlate well with the…

Optimization and Control · Mathematics 2021-06-15 Mert Gurbuzbalaban , Umut Şimşekli , Lingjiong Zhu

In overparameterized logistic regression, gradient descent (GD) iterates diverge in norm while converging in direction to the maximum $\ell_2$-margin solution -- a phenomenon known as the implicit bias of GD. This work investigates…

Machine Learning · Computer Science 2025-07-01 Jingfeng Wu , Peter Bartlett , Matus Telgarsky , Bin Yu

Most prior work on the convergence of gradient descent (GD) for overparameterized neural networks relies on strong assumptions on the step size (infinitesimal), the hidden-layer width (infinite), or the initialization (large, spectral,…

Machine Learning · Computer Science 2025-05-20 Ziqing Xu , Hancheng Min , Salma Tarmoun , Enrique Mallada , Rene Vidal

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Machine Learning · Computer Science 2026-01-01 Alan Oursland

We consider the well-studied setting of minimizing a convex Lipschitz function using either gradient descent (GD) or its stochastic variant (SGD), and examine the last iterate convergence. By now, it is known that standard stepsize choices…

Optimization and Control · Mathematics 2026-04-16 Guy Kornowski , Ohad Shamir

Deep learning models are increasingly popular in many machine learning applications where the training data may contain sensitive information. To provide formal and rigorous privacy guarantee, many learning systems now incorporate…

Machine Learning · Computer Science 2021-03-19 Xiangyi Chen , Zhiwei Steven Wu , Mingyi Hong

We study stochastic convex optimization (SCO) with heavy-tailed gradients under pure $\varepsilon$-differential privacy (DP). Instead of assuming a bound on the worst-case Lipschitz parameter of the loss, we assume only a bounded $k$-th…

Machine Learning · Computer Science 2026-05-06 Andrew Lowy

We study the generalization performance of unregularized gradient methods for separable linear classification. While previous work mostly deal with the binary case, we focus on the multiclass setting with $k$ classes and establish novel…

Machine Learning · Computer Science 2025-05-29 Matan Schliserman , Tomer Koren

We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamical system from a sequence of noisy observations generated by the system.…

Machine Learning · Computer Science 2019-02-12 Moritz Hardt , Tengyu Ma , Benjamin Recht

Empirically, modern deep learning training often occurs at the Edge of Stability (EoS), where the sharpness of the loss exceeds the threshold below which classical convergence analysis applies. Despite recent progress, existing theoretical…

Machine Learning · Computer Science 2026-04-14 Eric Gan

We consider non-convex stochastic optimization using first-order algorithms for which the gradient estimates may have heavy tails. We show that a combination of gradient clipping, momentum, and normalized gradient descent yields convergence…

Machine Learning · Computer Science 2021-11-10 Ashok Cutkosky , Harsh Mehta

Subgradient methods are the natural extension to the non-smooth case of the classical gradient descent for regular convex optimization problems. However, in general, they are characterized by slow convergence rates, and they require…

Optimization and Control · Mathematics 2023-11-20 Alessandro Scagliotti , Piero Colli Franzone

When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference. For example, in sequence-to-sequence modeling we are interested in high-quality translated…

Machine Learning · Computer Science 2020-10-05 Xi Gao , Han Zhang , Aliakbar Panahi , Tom Arodz

Real-world data is laden with outlying values. The challenge for machine learning is that the learner typically has no prior knowledge of whether the feedback it receives (losses, gradients, etc.) will be heavy-tailed or not. In this work,…

Machine Learning · Statistics 2020-12-16 Matthew J. Holland

Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep over-parameterized…

Machine Learning · Computer Science 2019-05-30 Simon S. Du , Jason D. Lee , Haochuan Li , Liwei Wang , Xiyu Zhai