English
Related papers

Related papers: Adaptive Newton Method for Empirical Risk Minimiza…

200 papers

Existing automatic data augmentation (DA) methods either ignore updating DA's parameters according to the target model's state during training or adopt update strategies that are not effective enough. In this work, we design a novel data…

Computer Vision and Pattern Recognition · Computer Science 2023-05-11 Xiaogang Xu , Hengshuang Zhao

In this paper, we introduce weight prediction into the AdamW optimizer to boost its convergence when training the deep neural network (DNN) models. In particular, ahead of each mini-batch training, we predict the future weights according to…

Machine Learning · Computer Science 2023-08-09 Lei Guan

Stochastic optimisation problems minimise expectations of random cost functions. We use 'optimise then discretise' method to solve stochastic optimisation. In our approach, accurate quadrature methods are required to calculate the…

Numerical Analysis · Mathematics 2022-02-22 Yuancheng Zhou

The generalization ability of minimizers of the empirical risk in the context of binary classification has been investigated under a wide variety of complexity assumptions for the collection of classifiers over which optimization is…

Statistics Theory · Mathematics 2019-01-21 Clémençon Stephan , Patrice Bertail , Guillaume Papa

We focus on the critical challenge of handling non-stationary data streams in online continual learning environments, where constrained storage capacity prevents complete retention of historical data, leading to catastrophic forgetting…

Methodology · Statistics 2025-08-12 Xinjia Lu , Chuhan Wang , Qian Zhao , Lixing Zhu , Xuehu Zhu

Traditional metrics like accuracy, F1-score, and precision are frequently used to evaluate machine learning models, however they may not be sufficient for evaluating performance on tiny, unbalanced, or high-dimensional datasets. A…

Machine Learning · Computer Science 2024-12-11 Serzhan Ossenov

This paper introduces AdaSDCA: an adaptive variant of stochastic dual coordinate ascent (SDCA) for solving the regularized empirical risk minimization problems. Our modification consists in allowing the method adaptively change the…

Optimization and Control · Mathematics 2015-03-02 Dominik Csiba , Zheng Qu , Peter Richtárik

Newton's method for finding an unconstrained minimizer for strictly convex functions, generally speaking, does not converge from any starting point. We introduce and study the damped regularized Newton's method (DRNM). It converges globally…

Optimization and Control · Mathematics 2017-06-27 Roman Polyak

Many statistical problems involve mixture models and the need for computationally efficient methods to estimate the mixing distribution has increased dramatically in recent years. Newton [Sankhya Ser. A 64 (2002) 306--322] proposed a fast…

Methodology · Statistics 2011-02-18 Ryan Martin , Jayanta K. Ghosh

This paper considers the decentralized consensus optimization problem defined over a network where each node holds a second-order differentiable local objective function. Our goal is to minimize the summation of local objective functions…

Optimization and Control · Mathematics 2020-08-25 Jiaojiao Zhang , Qing Ling , Anthony Man-Cho So

Imitation learning has enabled robots to perform complex, long-horizon tasks in challenging dexterous manipulation settings. As new methods are developed, they must be rigorously evaluated and compared against corresponding baselines…

This paper focuses on understanding how the generalization error scales with the amount of the training data for deep neural networks (DNNs). Existing techniques in statistical learning require computation of capacity measures, such as VC…

Machine Learning · Computer Science 2021-05-06 Devansh Bisla , Apoorva Nandini Saridena , Anna Choromanska

Optimizers like Adam and AdaGrad have been very successful in training large-scale neural networks. Yet, the performance of these methods is heavily dependent on a carefully tuned learning rate schedule. We show that in many large-scale…

Machine Learning · Computer Science 2022-02-02 Ehsan Amid , Rohan Anil , Christopher Fifty , Manfred K. Warmuth

Adam is one of the most popular optimization algorithms in deep learning. However, it is known that Adam does not converge in theory unless choosing a hyperparameter, i.e., $\beta_2$, in a problem-dependent manner. There have been many…

Second-order optimization methods are among the most widely used optimization approaches for convex optimization problems, and have recently been used to optimize non-convex optimization problems such as deep learning models. The widely…

Optimization and Control · Mathematics 2022-02-01 Dinesh Singh , Hardik Tankaria , Makoto Yamada

We consider a deep neural network estimator based on empirical risk minimization with l_1-regularization. We derive a general bound for its excess risk in regression and classification (including multiclass), and prove that it is adaptively…

Statistics Theory · Mathematics 2023-11-16 Felix Abramovich

Empirical risk minimization stands behind most optimization in supervised machine learning. Under this scheme, labeled data is used to approximate an expected cost (risk), and a learning algorithm updates model-defining parameters in search…

Machine Learning · Statistics 2023-05-25 James Schmidt

In this paper, we propose and analyze some practical Newton methods for electronic structure calculations. We show the convergence and the local quadratic convergence rate for the Newton method when the Newton search directions are…

Optimization and Control · Mathematics 2020-01-28 Xiaoying Dai , Liwei Zhang , Aihui Zhou

Modern statistical inference tasks often require iterative optimization methods to compute the solution. Convergence analysis from an optimization viewpoint only informs us how well the solution is approximated numerically but overlooks the…

Machine Learning · Statistics 2020-07-27 Tengyuan Liang , Weijie Su

We consider distributed convex optimization problems originated from sample average approximation of stochastic optimization, or empirical risk minimization in machine learning. We assume that each machine in the distributed computing…

Optimization and Control · Mathematics 2015-01-05 Yuchen Zhang , Lin Xiao