English
Related papers

Related papers: An iterative K-FAC algorithm for Deep Learning

200 papers

Influence functions offer a principled way to trace model predictions back to training data, but their use in deep learning is hampered by the need to invert a large, ill-conditioned Hessian matrix. Approximations such as Generalised…

Machine Learning · Computer Science 2026-02-17 Steve Hong , Runa Eschenhagen , Bruno Mlodozeniec , Richard Turner

This paper introduces a new stochastic optimization method based on the regularized Fisher information matrix (FIM), named SOFIM, which can efficiently utilize the FIM to approximate the Hessian matrix for finding Newton's gradient update…

Machine Learning · Computer Science 2024-05-02 Mrinmay Sen , A. K. Qin , Gayathri C , Raghu Kishore N , Yen-Wei Chen , Balasubramanian Raman

Federated learning (FL) for minimax optimization has emerged as a powerful paradigm for training models across distributed nodes/clients while preserving data privacy and model robustness on data heterogeneity. In this work, we delve into…

Machine Learning · Computer Science 2024-05-09 Chris Junchi Li

We present a new algorithm, FRiM (FRactal Iterative Method), aiming at the reconstruction of the optical wavefront from measurements provided by a wavefront sensor. As our application is adaptive optics on extremely large telescopes, our…

Mathematical Physics · Physics 2015-05-18 Eric Thiebaut , Michel Tallon

Dose reduction in computed tomography (CT) is essential for decreasing radiation risk in clinical applications. Iterative reconstruction is one of the most promising ways to compensate for the increased noise due to reduction of photon…

Image and Video Processing · Electrical Eng. & Systems 2021-03-24 Zhuonan He , Yikun Zhang , Yu Guan , Shanzhou Niu , Yi Zhang , Yang Chen , Qiegen Liu

The success of deep learning hinges on enormous data and large models, which require labor-intensive annotations and heavy computation costs. Subset selection is a fundamental problem that can play a key role in identifying smaller portions…

Machine Learning · Computer Science 2023-12-19 Srikumar Ramalingam , Pranjal Awasthi , Sanjiv Kumar

In this paper we propose and study a technique to reduce the number of parameters and computation time in fully-connected layers of neural networks using Kronecker product, at a mild cost of the prediction quality. The technique proceeds by…

Neural and Evolutionary Computing · Computer Science 2015-07-23 Shuchang Zhou , Jia-Nan Wu

We consider the development of practical stochastic quasi-Newton, and in particular Kronecker-factored block-diagonal BFGS and L-BFGS methods, for training deep neural networks (DNNs). In DNN training, the number of variables and components…

Machine Learning · Computer Science 2021-01-11 Donald Goldfarb , Yi Ren , Achraf Bahamou

We present a clustering- and demotion-based algorithm called Kmeans-FOLD to induce nonmonotonic logic programs from positive and negative examples. Our algorithm improves upon-and is inspired by-the FOLD algorithm. The FOLD algorithm itself…

Artificial Intelligence · Computer Science 2021-09-28 Huaduo Wang , Farhad Shakerin , Gopal Gupta

The holy grail of machine learning is to enable Continual Federated Learning (CFL) to enhance the efficiency, privacy, and scalability of AI systems while learning from streaming data. The primary challenge of a CFL system is to overcome…

Machine Learning · Computer Science 2025-11-11 Satish Kumar Keshri , Nazreen Shah , Ranjitha Prasad

Coarse-grained (CG) molecular simulations have become a standard tool to study molecular processes on time- and length-scales inaccessible to all-atom simulations. Parameterizing CG force fields to match all-atom simulations has mainly…

Computational Physics · Physics 2023-02-07 Jonas Köhler , Yaoyi Chen , Andreas Krämer , Cecilia Clementi , Frank Noé

Efficient k-nearest neighbor search is a fundamental task, foundational for many problems in NLP. When the similarity is measured by dot-product between dual-encoder vectors or $\ell_2$-distance, there already exist many scalable and…

Computation and Language · Computer Science 2022-10-25 Nishant Yadav , Nicholas Monath , Rico Angell , Manzil Zaheer , Andrew McCallum

We propose a new algorithm for finite sum optimization which we call the curvature-aided incremental aggregated gradient (CIAG) method. Motivated by the problem of training a classifier for a d-dimensional problem, where the number of…

Machine Learning · Statistics 2017-10-26 Hoi-To Wai , Wei Shi , Angelia Nedic , Anna Scaglione

Adaptive regularization methods that exploit more than the diagonal entries exhibit state of the art performance for many tasks, but can be prohibitive in terms of memory and running time. We find the spectra of the Kronecker-factored…

Machine Learning · Statistics 2023-10-18 Vladimir Feinberg , Xinyi Chen , Y. Jennifer Sun , Rohan Anil , Elad Hazan

Coarse-graining (CG) of molecular simulations simplifies the particle representation by grouping selected atoms into pseudo-beads and drastically accelerates simulation. However, such CG procedure induces information losses, which makes…

Machine Learning · Computer Science 2022-06-20 Wujie Wang , Minkai Xu , Chen Cai , Benjamin Kurt Miller , Tess Smidt , Yusu Wang , Jian Tang , Rafael Gómez-Bombarelli

This work proposes a Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 updates, called MKOR, that improves the training time and convergence properties of deep neural networks (DNNs). Second-order techniques, while enjoying…

Machine Learning · Computer Science 2024-01-31 Mohammad Mozaffari , Sikan Li , Zhao Zhang , Maryam Mehri Dehnavi

Gradient descent method, as one of the major methods in numerical optimization, is the key ingredient in many machine learning algorithms. As one of the most fundamental way to solve the optimization problems, it promises the function value…

Quantum Physics · Physics 2021-02-01 Keren Li , Shijie Wei , Feihao Zhang , Pan Gao , Zengrong Zhou , Tao Xin , Xiaoting Wang , Guilu Long

Successive quadratic approximations, or second-order proximal methods, are useful for minimizing functions that are a sum of a smooth part and a convex, possibly nonsmooth part that promotes regularization. Most analyses of iteration…

Optimization and Control · Mathematics 2019-01-25 Ching-pei Lee , Stephen J. Wright

Despite the predominant use of first-order methods for training deep learning models, second-order methods, and in particular, natural gradient methods, remain of interest because of their potential for accelerating training through the use…

Machine Learning · Computer Science 2021-12-23 Yi Ren , Donald Goldfarb

Variational Bayesian neural nets combine the flexibility of deep learning with Bayesian uncertainty estimation. Unfortunately, there is a tradeoff between cheap but simple variational families (e.g.~fully factorized) or expensive and…

Machine Learning · Computer Science 2018-02-27 Guodong Zhang , Shengyang Sun , David Duvenaud , Roger Grosse