English
Related papers

Related papers: Surfing: Iterative optimization over incrementally…

200 papers

The isolated toughness variant is a salient parameter for measuring the vulnerability of networks, which is inherently related to fractional factors (used to characterize the feasibility of data transmission). The combination of minimum…

Combinatorics · Mathematics 2024-08-21 Wei Gao , Yaojun Chen , Hainan Zhang

We propose a new stochastic optimization framework for empirical risk minimization problems such as those that arise in machine learning. The traditional approaches, such as (mini-batch) stochastic gradient descent (SGD), utilize an…

Machine Learning · Statistics 2020-02-04 Kenji Kawaguchi , Haihao Lu

Factorized layers--operations parameterized by products of two or more matrices--occur in a variety of deep learning contexts, including compressed model training, certain types of knowledge distillation, and multi-head self-attention…

Machine Learning · Statistics 2022-10-07 Mikhail Khodak , Neil Tenenholtz , Lester Mackey , Nicolò Fusi

We develop a learning-based control algorithm for unknown dynamical systems under very severe data limitations. Specifically, the algorithm has access to streaming and noisy data only from a single and ongoing trial. It accomplishes such…

Systems and Control · Electrical Eng. & Systems 2021-12-30 Franck Djeumou , Ufuk Topcu

We study the dynamics of optimization and the generalization properties of one-hidden layer neural networks with quadratic activation function in the over-parametrized regime where the layer width $m$ is larger than the input dimension $d$.…

Machine Learning · Computer Science 2021-03-22 Stefano Sarao Mannelli , Eric Vanden-Eijnden , Lenka Zdeborová

One of the most important parts of Artificial Neural Networks is minimizing the loss functions which tells us how good or bad our model is. To minimize these losses we need to tune the weights and biases. Also to calculate the minimum value…

Machine Learning · Computer Science 2021-01-08 Kaustubh Yadav

Many modern sequential recommender systems use deep neural networks, which can effectively estimate the relevance of items but require a lot of time to train. Slow training increases expenses, hinders product development timescales and…

Information Retrieval · Computer Science 2022-07-18 Aleksandr Petrov , Craig Macdonald

We study dual-based algorithms for distributed convex optimization problems over networks, where the objective is to minimize a sum $\sum_{i=1}^{m}f_i(z)$ of functions over in a network. We provide complexity bounds for four different…

Optimization and Control · Mathematics 2020-03-17 César A. Uribe , Soomin Lee , Alexander Gasnikov , Angelia Nedić

When and why can a neural network be successfully trained? This article provides an overview of optimization algorithms and theory for training neural networks. First, we discuss the issue of gradient explosion/vanishing and the more…

Machine Learning · Computer Science 2019-12-21 Ruoyu Sun

Deep networks realize complex mappings that are often understood by their locally linear behavior at or around points of interest. For example, we use the derivative of the mapping with respect to its inputs for sensitivity analysis, or to…

Machine Learning · Computer Science 2019-07-09 Guang-He Lee , David Alvarez-Melis , Tommi S. Jaakkola

We propose a new algorithm for minimizing regularized empirical loss: Stochastic Dual Newton Ascent (SDNA). Our method is dual in nature: in each iteration we update a random subset of the dual variables. However, unlike existing methods…

Machine Learning · Computer Science 2015-02-10 Zheng Qu , Peter Richtárik , Martin Takáč , Olivier Fercoq

This paper investigates multilevel initialization strategies for training very deep neural networks with a layer-parallel multigrid solver. The scheme is based on the continuous interpretation of the training problem as a problem of optimal…

Machine Learning · Computer Science 2019-12-20 Eric C. Cyr , Stefanie Günther , Jacob B. Schroder

We study the task of selecting $k$ nodes, in a social network of size $n$, to seed a diffusion with maximum expected spread size, under the independent cascade model with cascade probability $p$. Most of the previous work on this problem…

Social and Information Networks · Computer Science 2022-05-24 Dean Eckles , Hossein Esfandiari , Elchanan Mossel , M. Amin Rahimian

We study the training dynamics of a shallow neural network with quadratic activation functions and quadratic cost in a teacher-student setup. In line with previous works on the same neural architecture, the optimization is performed…

Optimization and Control · Mathematics 2023-11-08 Simon Martin , Francis Bach , Giulio Biroli

Efficient model selection for identifying a suitable pre-trained neural network to a downstream task is a fundamental yet challenging task in deep learning. Current practice requires expensive computational costs in model training for…

Machine Learning · Computer Science 2022-01-19 Chunheng Jiang , Tejaswini Pedapati , Pin-Yu Chen , Yizhou Sun , Jianxi Gao

The article presents a new method of linear programming, called the surface movement method. This method constructs an optimal objective path on the surface of the feasible polytope from the initial boundary point to the point at which the…

Optimization and Control · Mathematics 2024-04-22 Nikolay A. Olkhovsky , Leonid B. Sokolinsky

We consider training over-parameterized two-layer neural networks with Rectified Linear Unit (ReLU) using gradient descent (GD) method. Inspired by a recent line of work, we study the evolutions of network prediction errors across GD…

Machine Learning · Computer Science 2019-09-04 Lili Su , Pengkun Yang

A striking observation about iterative magnitude pruning (IMP; Frankle et al. 2020) is that $\unicode{x2014}$ after just a few hundred steps of dense training $\unicode{x2014}$ the method can find a sparse sub-network that can be trained to…

Machine Learning · Computer Science 2022-06-06 Mansheej Paul , Brett W. Larsen , Surya Ganguli , Jonathan Frankle , Gintare Karolina Dziugaite

In this paper we first identify a basic limitation in gradient descent-based optimization methods when used in conjunctions with smooth kernels. An analysis based on the spectral properties of the kernel demonstrates that only a vanishingly…

Machine Learning · Statistics 2017-06-20 Siyuan Ma , Mikhail Belkin

We develop a neural-network framework for multi-period risk--reward stochastic control problems with constrained two-step feedback policies that may be discontinuous in the state. We allow a broad class of objectives built on a…

Computational Finance · Quantitative Finance 2026-03-09 Chang Chen , Duy-Minh Dang