English
Related papers

Related papers: Convergence and Implicit Bias of Gradient Descent …

200 papers

A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and stochasticity of the distributed data. In this work, we show…

Machine Learning · Computer Science 2021-12-14 Yatin Dandi , Luis Barba , Martin Jaggi

This paper presents fault-tolerant asynchronous Stochastic Gradient Descent (SGD) algorithms. SGD is widely used for approximating the minimum of a cost function $Q$, as a core part of optimization and learning algorithms. Our algorithms…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-06-14 Hagit Attiya , Noa Schiller

Recent advances in meta-learning has led to remarkable performances on several few-shot learning benchmarks. However, such success often ignores the similarity between training and testing tasks, resulting in a potential bias evaluation.…

Machine Learning · Computer Science 2021-01-28 Cuong Nguyen , Thanh-Toan Do , Gustavo Carneiro

Continual learning (CL) is a setting in which an agent has to learn from an incoming stream of data during its entire lifetime. Although major advances have been made in the field, one recurring problem which remains unsolved is that of…

Machine Learning · Computer Science 2021-02-26 Thang Doan , Mehdi Bennani , Bogdan Mazoure , Guillaume Rabusseau , Pierre Alquier

We consider regression of a max-affine model that produces a piecewise linear model by combining affine models via the max function. The max-affine model ubiquitously arises in applications in signal processing and statistics including…

Machine Learning · Statistics 2023-08-17 Seonho Kim , Kiryung Lee

In this work, we investigate the margin-maximization bias exhibited by gradient-based algorithms in classifying linearly separable data. We present an in-depth analysis of the specific properties of the velocity field associated with…

Machine Learning · Computer Science 2024-12-30 Mingze Wang , Zeping Min , Lei Wu

In this work, we study an optimizer, Grad-Avg to optimize error functions. We establish the convergence of the sequence of iterates of Grad-Avg mathematically to a minimizer (under boundedness assumption). We apply Grad-Avg along with some…

Machine Learning · Computer Science 2020-12-11 Saugata Purkayastha , Sukannya Purkayastha

Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem. Recently, \citet{zhang2019gradient} show that clipped (stochastic) Gradient Descent (GD)…

Machine Learning · Computer Science 2020-10-30 Bohang Zhang , Jikai Jin , Cong Fang , Liwei Wang

When using stochastic gradient descent to solve large-scale machine learning problems, a common practice of data processing is to shuffle the training data, partition the data across multiple machines if needed, and then perform several…

Machine Learning · Statistics 2017-10-02 Qi Meng , Wei Chen , Yue Wang , Zhi-Ming Ma , Tie-Yan Liu

We consider the problem of simultaneously learning to linearly combine a very large number of kernels and learn a good predictor based on the learnt kernel. When the number of kernels $d$ to be combined is very large, multiple kernel…

Machine Learning · Computer Science 2015-03-20 Arash Afkanpour , András György , Csaba Szepesvári , Michael Bowling

A new loss function is proposed for neural networks on classification tasks which extends the hinge loss by assigning gradients to its critical points. We will show that for a linear classifier on linearly separable data with fixed step…

Machine Learning · Computer Science 2020-06-26 Justin Lizama

We analyze the implicit bias of constant step stochastic subgradient descent (SGD). We consider the setting of binary classification with homogeneous neural networks - a large class of deep neural networks with ReLU-type activation…

Machine Learning · Computer Science 2025-07-18 Sholom Schechtman , Nicolas Schreuder

We analyze task orderings in continual learning for linear regression, assuming joint realizability of training data. We focus on orderings that greedily maximize dissimilarity between consecutive tasks, a concept briefly explored in prior…

Machine Learning · Computer Science 2025-10-24 Matan Tsipory , Ran Levinstein , Itay Evron , Mark Kong , Deanna Needell , Daniel Soudry

Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their…

Machine Learning · Computer Science 2024-05-17 Zenglin Shi , Pei Liu , Tong Su , Yunpeng Wu , Kuien Liu , Yu Song , Meng Wang

The discrete logarithm problem is a fundamental challenge in number theory with significant implications for cryptographic protocols. In this paper, we investigate the limitations of gradient-based methods for learning the parity bit of the…

Machine Learning · Computer Science 2023-10-04 Rustem Takhanov , Maxat Tezekbayev , Artur Pak , Arman Bolatov , Zhibek Kadyrsizova , Zhenisbek Assylbekov

Over the past years, there has been significant interest in understanding the implicit bias of gradient descent optimization and its connection to the generalization properties of overparametrized neural networks. Several works observed…

Optimization and Control · Mathematics 2025-03-11 Hung-Hsu Chou , Johannes Maly , Claudio Mayrink Verdun , Bernardo Freitas Paulo da Costa , Heudson Mirandola

In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic forgetting even when they are trained to approximate a single target distribution. We show that GAN training is a continual learning problem in…

Machine Learning · Computer Science 2020-03-24 Hoang Thanh-Tung , Truyen Tran

Continual learning has been an active research area in machine learning, focusing on incrementally learning a sequence of tasks. A key challenge is catastrophic forgetting (CF), and most research efforts have been directed toward mitigating…

Machine Learning · Computer Science 2025-02-27 Saleh Momeni , Bing Liu

Transformer models have emerged as fundamental tools across various scientific and engineering disciplines, owing to their outstanding performance in diverse applications. Despite this empirical success, the theoretical foundations of…

Machine Learning · Computer Science 2026-04-14 Zhen Qin , Jinxin Zhou , Jiachen Jiang , Zhihui Zhu

The convergence of GD and SGD when training mildly parameterized neural networks starting from random initialization is studied. For a broad range of models and loss functions, including the most commonly used square loss and cross entropy…

Machine Learning · Computer Science 2023-05-30 Mingze Wang , Chao Ma