English
Related papers

Related papers: Gauss-Newton Temporal Difference Learning with Non…

200 papers

Solving high-dimensional partial differential equations (PDEs) is a major challenge in scientific computing. We develop a new numerical method for solving elliptic-type PDEs by adapting the Q-learning algorithm in reinforcement learning.…

Numerical Analysis · Mathematics 2023-06-27 Samuel N. Cohen , Deqing Jiang , Justin Sirignano

We developed a Nonlinear Level-set Learning (NLL) method for dimensionality reduction in high-dimensional function approximation with small data. This work is motivated by a variety of design tasks in real-world engineering applications,…

Functional Analysis · Mathematics 2019-06-20 Guannan Zhang , Jiaxin Zhang , Jacob Hinkle

The recent emergence of deep learning has led to a great deal of work on designing supervised deep semantic segmentation algorithms. As in many tasks sufficient pixel-level labels are very difficult to obtain, we propose a method which…

Computer Vision and Pattern Recognition · Computer Science 2024-04-19 Matthias Schwab , Agnes Mayr , Markus Haltmeier

Non-stationary environments pose a fundamental challenge for deep reinforcement learning, as changes in dynamics or rewards invalidate learned value functions and cause catastrophic forgetting. We propose \emph{Gradient-Boosted Deep…

Machine Learning · Computer Science 2025-12-22 Chang-Hwan Lee , Chanseung Lee

We study the problem of training a two-layer neural network (NN) of arbitrary width using stochastic gradient descent (SGD) where the input $\boldsymbol{x}\in \mathbb{R}^d$ is Gaussian and the target $y \in \mathbb{R}$ follows a…

Machine Learning · Statistics 2023-03-17 Alireza Mousavi-Hosseini , Sejun Park , Manuela Girotti , Ioannis Mitliagkas , Murat A. Erdogdu

Second-order methods for neural network optimization have several advantages over methods based on first-order gradient descent, including better scaling to large mini-batch sizes and fewer updates needed for convergence. But they are…

Machine Learning · Computer Science 2017-12-21 Huishuai Zhang , Caiming Xiong , James Bradbury , Richard Socher

In this manuscript, we propose a general proximal quasi-Newton method tailored for nonconvex and nonsmooth optimization problems, where we do not require the sequence of the variable metric (or Hessian approximation) to be uniformly bounded…

Optimization and Control · Mathematics 2025-07-28 Xiaoxi Jia

We propose a new per-layer adaptive step-size procedure for stochastic first-order optimization methods for minimizing empirical loss functions in deep learning, eliminating the need for the user to tune the learning rate (LR). The proposed…

Machine Learning · Computer Science 2023-07-07 Achraf Bahamou , Donald Goldfarb

The majority of model-based learned image reconstruction methods in medical imaging have been limited to uniform domains, such as pixelated images. If the underlying model is solved on nonuniform meshes, arising from a finite element method…

Image and Video Processing · Electrical Eng. & Systems 2021-07-12 William Herzberg , Daniel B. Rowe , Andreas Hauptmann , Sarah J. Hamilton

As one of the most fundamental tasks in graph theory, subgraph matching is a crucial task in many fields, ranging from information retrieval, computer vision, biology, chemistry and natural language processing. Yet subgraph matching problem…

Machine Learning · Computer Science 2022-09-19 Zixun Lan , Limin Yu , Linglong Yuan , Zili Wu , Qiang Niu , Fei Ma

Motivated by the recent empirical successes of deep generative models, we study the computational complexity of the following unsupervised learning problem. For an unknown neural network $F:\mathbb{R}^d\to\mathbb{R}^{d'}$, let $D$ be the…

Machine Learning · Computer Science 2022-06-01 Sitan Chen , Jerry Li , Yuanzhi Li

Neural networks are trained by optimizing multi-dimensional sets of fitting parameters on non-convex loss landscapes. Low-loss regions of the landscapes correspond to the parameter sets that perform well on the training data. A key issue in…

Machine Learning · Computer Science 2026-02-26 Jianneng Yu , Alexandre V. Morozov

We study policy evaluation problems in multi-task reinforcement learning (RL) under a low-rank representation setting. In this setting, we are given $N$ learning tasks where the corresponding value function of these tasks lie in an…

Machine Learning · Computer Science 2025-03-05 Yitao Bai , Sihan Zeng , Justin Romberg , Thinh T. Doan

A convergence analysis is developed for the regularized Newton method for training neural networks (NNs) in the overparameterized limit. As the number of hidden units tends to infinity, the NN training dynamics converge in probability to…

Machine Learning · Computer Science 2026-05-21 Konstantin Riedl , Konstantinos Spiliopoulos , Justin Sirignano

Nonuniform rotational distortion (NURD) correction is vital for endoscopic optical coherence tomography (OCT) imaging and its functional extensions, such as angiography and elastography. Current NURD correction methods require…

Image and Video Processing · Electrical Eng. & Systems 2024-01-08 Haoran Zhang , Jianlong Yang , Jingqian Zhang , Shiqing Zhao , Aili Zhang

Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are…

Machine Learning · Computer Science 2019-05-24 Fan Zhou , Chengtai Cao , Kunpeng Zhang , Goce Trajcevski , Ting Zhong , Ji Geng

When learning graph neural networks (GNNs) in node-level prediction tasks, most existing loss functions are applied for each node independently, even if node embeddings and their labels are non-i.i.d. because of their graph structures. To…

Machine Learning · Computer Science 2024-03-14 Minjie Cheng , Hongteng Xu

Recently proposed Gated Linear Networks present a tractable nonlinear network architecture, and exhibit interesting capabilities such as learning with local error signals and reduced forgetting in sequential learning. In this work, we…

Machine Learning · Computer Science 2022-12-13 Qianyi Li , Haim Sompolinsky

Reinforcement learning (RL) has been successfully used to solve many continuous control tasks. Despite its impressive results however, fundamental questions regarding the sample complexity of RL on continuous problems remain open. We study…

Machine Learning · Computer Science 2017-12-27 Stephen Tu , Benjamin Recht

Voice-assistants text classification and named-entity recognition (NER) models are trained on millions of example utterances. Because of the large datasets, long training time is one of the bottlenecks for releasing improved models. In this…

Computation and Language · Computer Science 2019-02-28 Stanislav Peshterliev , Alexander Hsieh , Imre Kiss