English
Related papers

Related papers: Low-Variance Gradient Estimation in Unrolled Compu…

200 papers

We propose a population-based Evolutionary Stochastic Gradient Descent (ESGD) framework for optimizing deep neural networks. ESGD combines SGD and gradient-free evolutionary algorithms as complementary algorithms in one framework in which…

Machine Learning · Computer Science 2018-10-17 Xiaodong Cui , Wei Zhang , Zoltán Tüske , Michael Picheny

Many applications in machine learning require optimizing a function whose true gradient is unknown, but where surrogate gradient information (directions that may be correlated with, but not necessarily identical to, the true gradient) is…

Neural and Evolutionary Computing · Computer Science 2019-06-12 Niru Maheswaranathan , Luke Metz , George Tucker , Dami Choi , Jascha Sohl-Dickstein

We present a simple nonadaptive randomized algorithm that estimates the number of edges in a simple, unweighted, undirected graph, possibly containing isolated vertices, using only degree and random edge queries. For an $n$-vertex graph,…

Data Structures and Algorithms · Computer Science 2025-12-16 Arijit Bishnu , Debarshi Chanda , Buddha Dev Das , Arijit Ghosh , Gopinath Mishra

Stochastic approximation (SA) is a key method used in statistical learning. Recently, its non-asymptotic convergence analysis has been considered in many papers. However, most of the prior analyses are made under restrictive assumptions…

Machine Learning · Statistics 2019-06-18 Belhal Karimi , Blazej Miasojedow , Eric Moulines , Hoi-To Wai

Evolution Strategies (ESs) have recently become popular for training deep neural networks, in particular on reinforcement learning tasks, a special form of controller design. Compared to classic problems in continuous direct search, deep…

Neural and Evolutionary Computing · Computer Science 2018-07-03 Nils Müller , Tobias Glasmachers

Discrete latent bottlenecks in variational autoencoders (VAEs) offer high bit efficiency and can be modeled with autoregressive discrete distributions, enabling parameter-efficient multimodal search with transformers. However, discrete…

Machine Learning · Computer Science 2026-02-12 Michael Drolet , Firas Al-Hafez , Aditya Bhatt , Jan Peters , Oleg Arenz

We propose and illustrate an approach to coarse-graining the dynamics of evolving networks (networks whose connectivity changes dynamically). The approach is based on the equation-free framework: short bursts of detailed network evolution…

Social and Information Networks · Computer Science 2012-02-28 Katherine A. Bold , Karthikeyan Rajendran , Balázs Ráth , Ioannis G. Kevrekidis

Gaussian smoothing (GS) is a derivative-free optimization (DFO) algorithm that estimates the gradient of an objective using perturbations of the current parameters sampled from a standard normal distribution. We generalize it to sampling…

Machine Learning · Computer Science 2022-11-29 Katelyn Gao , Ozan Sener

Solving the Goal-Conditioned Reward Sparse (GCRS) task is a challenging reinforcement learning problem due to the sparsity of reward signals. In this work, we propose a new formulation of GCRS tasks from the perspective of the drifted…

Machine Learning · Computer Science 2020-05-01 Hao Sun , Xinyu Pan , Bo Dai , Dahua Lin , Bolei Zhou

In this paper, we develop a new optimization framework for the least squares learning problem via fully connected neural networks or physics-informed neural networks. The gradient descent sometimes behaves inefficiently in deep learning…

Machine Learning · Computer Science 2025-05-01 Yaru Liu , Yiqi Gu , Michael K. Ng

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when…

Machine Learning · Computer Science 2020-06-11 Tao Lin , Lingjing Kong , Sebastian U. Stich , Martin Jaggi

We consider the task of learning Ising models when the signs of different random variables are flipped independently with possibly unequal, unknown probabilities. In this paper, we focus on the problem of robust estimation of…

Machine Learning · Statistics 2020-06-11 Ashish Katiyar , Vatsal Shah , Constantine Caramanis

In an increasing number of applications, it is of interest to recover an approximately low-rank data matrix from noisy observations. This paper develops an unbiased risk estimate---holding in a Gaussian model---for any spectral estimator…

Statistics Theory · Mathematics 2015-06-11 Emmanuel J. Candes , Carlos A. Sing-Long , Joshua D. Trzasko

In a number of situations, collecting a function value for every data point may be prohibitively expensive, and random sampling ignores any structure in the underlying data. We introduce a scalable optimization algorithm with no correction…

Machine Learning · Computer Science 2020-06-23 Saeed Vahidian , Baharan Mirzasoleiman , Alexander Cloninger

Stochastic gradient descent is the most prevalent algorithm to train neural networks. However, other approaches such as evolutionary algorithms are also applicable to this task. Evolutionary algorithms bring unique trade-offs that are worth…

Neural and Evolutionary Computing · Computer Science 2018-06-27 Jonas Prellberg , Oliver Kramer

Currently, Deep Convolutional Neural Networks (DCNNs) are used to solve all kinds of problems in the field of machine learning and artificial intelligence due to their learning and adaptation capabilities. However, most successful DCNN…

Neural and Evolutionary Computing · Computer Science 2020-12-01 Francisco Erivaldo Fernandes Junior , Gary G. Yen

A new algorithm named EXPected Similarity Estimation (EXPoSE) was recently proposed to solve the problem of large-scale anomaly detection. It is a non-parametric and distribution free kernel method based on the Hilbert space embedding of…

Machine Learning · Computer Science 2015-11-18 Markus Schneider , Wolfgang Ertel , Günther Palm

Sketch-and-solve (SAS) is a very successful method to efficiently estimate the solution of heavily overdetermined large linear least squares problems. It uses random sketching to reduce the size of the problem, hence reducing the…

Numerical Analysis · Mathematics 2026-05-26 Irina-Beatrice Haas , Michael B. Giles , Yuji Nakatsukasa

A key challenge in the continual learning setting is to efficiently learn a sequence of tasks without forgetting how to perform previously learned tasks. Many existing approaches to this problem work by either retraining the model on…

Machine Learning · Computer Science 2024-01-12 Weijieying Ren , Vasant G Honavar

Stochastic gradient methods are dominant in nonconvex optimization especially for deep models but have low asymptotical convergence due to the fixed smoothness. To address this problem, we propose a simple yet effective method for improving…

Machine Learning · Computer Science 2018-05-25 Jun Li , Hongfu Liu , Bineng Zhong , Yue Wu , Yun Fu