English
Related papers

Related papers: Revisiting Scalable Hessian Diagonal Approximation…

200 papers

Neural network pruning is a practical way for reducing the size of trained models and the number of floating-point operations. One way of pruning is to use the relative Hessian trace to calculate sensitivity of each channel, as compared to…

Computer Vision and Pattern Recognition · Computer Science 2023-06-13 Jack Chong , Manas Gupta , Lihui Chen

Conventional scaling of neural networks typically involves designing a base network and growing different dimensions like width, depth, etc. of the same by some predefined scaling factors. We introduce an automated scaling approach…

Machine Learning · Computer Science 2024-02-21 Akash Guna R. T , Arnav Chavan , Deepak Gupta

We introduce a finite-difference framework for curvature regularization in neural signed distance field (SDF) learning. Existing approaches enforce curvature priors using full Hessian information obtained via second-order automatic…

Graphics · Computer Science 2025-11-13 Haotian Yin , Aleksander Plocharski , Michal Jan Wlodarczyk , Przemyslaw Musialski

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

We consider the minimization of a continuous function over the intersection of a regular cone with an affine set via a new class of adaptive first- and second-order optimization methods, building on the Hessian-barrier techniques introduced…

Optimization and Control · Mathematics 2022-10-18 Pavel Dvurechensky , Mathias Staudigl

In this paper, we consider derivative free optimization problems, where the objective function is smooth but is computed with some amount of noise, the function evaluations are expensive and no derivative information is available. We are…

Optimization and Control · Mathematics 2019-06-05 Albert S Berahas , Liyuan Cao , Krzysztof Choromanski , Katya Scheinberg

It is commonly believed that scaling language models should commit a significant space or time cost, by increasing the parameters (parameter scaling) or output tokens (inference-time scaling). We introduce the third and more…

Machine Learning · Computer Science 2025-05-16 Mouxiang Chen , Binyuan Hui , Zeyu Cui , Jiaxi Yang , Dayiheng Liu , Jianling Sun , Junyang Lin , Zhongxin Liu

Several machine learning applications involve the optimization of higher-order derivatives (e.g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation. As a…

Machine Learning · Computer Science 2020-11-26 Tianyu Pang , Kun Xu , Chongxuan Li , Yang Song , Stefano Ermon , Jun Zhu

This work considers the non-convex finite sum minimization problem. There are several algorithms for such problems, but existing methods often work poorly when the problem is badly scaled and/or ill-conditioned, and a primary goal of this…

Deep active learning (AL) selects batches of instances for annotation to avoid retraining deep neural networks (DNNs) after each new label. Employing a naive top-$b$ selection can result in a batch of redundant (similar) instances. To…

Machine Learning · Computer Science 2026-03-12 Denis Huseljic , Marek Herde , Lukas Rauch , Paul Hahn , Zhixin Huang , Daniel Kottke , Stephan Vogt , Bernhard Sick

We propose an algorithm for inexpensive gradient-based hyperparameter optimization that combines the implicit function theorem (IFT) with efficient inverse Hessian approximations. We present results about the relationship between the IFT…

Machine Learning · Computer Science 2019-11-11 Jonathan Lorraine , Paul Vicol , David Duvenaud

Second-order information, in the form of Hessian- or Inverse-Hessian-vector products, is a fundamental tool for solving optimization problems. Recently, there has been significant interest in utilizing this information in the context of…

Machine Learning · Computer Science 2020-11-26 Sidak Pal Singh , Dan Alistarh

The Hessian spectrum of trained deep networks exhibits a characteristic structure: a continuous bulk of near-zero eigenvalues and a small number of large outlier eigenvalues (spikes), confirming the relevance of Random Matrix Theory in deep…

Machine Learning · Computer Science 2026-05-19 Hugo Vigna , Samuel Bontemps

This paper proposes a family of online second order methods for possibly non-convex stochastic optimizations based on the theory of preconditioned stochastic gradient descent (PSGD), which can be regarded as an enhance stochastic Newton…

Machine Learning · Statistics 2018-05-01 Xi-Lin Li

In the Bayesian approach to inverse problems, data are often informative, relative to the prior, only on a low-dimensional subspace of the parameter space. Significant computational savings can be achieved by using this subspace to…

Numerical Analysis · Mathematics 2015-07-07 Alessio Spantini , Antti Solonen , Tiangang Cui , James Martin , Luis Tenorio , Youssef Marzouk

Gradient-based algorithms are one of the methods of choice for the optimisation of Markov Decision Processes. In this article we will present a novel approximate Newton algorithm for the optimisation of such models. The algorithm has…

Optimization and Control · Mathematics 2015-08-05 Thomas Furmston , David Barber

Quantum neural networks (QNNs) offer a powerful paradigm for programming near-term quantum computers and have the potential to speedup applications ranging from data science to chemistry to materials science. However, a possible obstacle to…

Quantum Physics · Physics 2021-06-08 M. Cerezo , Patrick J. Coles

Novel computer vision architectures monopolize the spotlight, but the impact of the model architecture is often conflated with simultaneous changes to training methodology and scaling strategies. Our work revisits the canonical ResNet (He…

Computer Vision and Pattern Recognition · Computer Science 2021-03-16 Irwan Bello , William Fedus , Xianzhi Du , Ekin D. Cubuk , Aravind Srinivas , Tsung-Yi Lin , Jonathon Shlens , Barret Zoph

Training deep neural networks is a structured optimization problem, because the parameters are naturally represented by matrices and tensors rather than by vectors. Under this structural representation, it has been widely observed that…

Machine Learning · Computer Science 2025-10-30 Kang An , Yuxing Liu , Rui Pan , Yi Ren , Shiqian Ma , Donald Goldfarb , Tong Zhang

Backpropagation (BP) is the standard algorithm for training the deep neural networks that power modern artificial intelligence including large language models. However, BP is energy inefficient and unlikely to be implemented by the brain.…

Machine Learning · Computer Science 2025-10-30 Francesco Innocenti