English
Related papers

Related papers: Generalized Doubly Reparameterized Gradient Estima…

200 papers

In this paper we investigate the generalization error of gradient descent (GD) applied to an $\ell_2$-regularized OLS objective function in the linear model. Based on our analysis we develop new methodology for computationally tractable and…

Statistics Theory · Mathematics 2026-01-27 Thomas Stark , Lukas Steinberger

We propose Deep Residual Mixture Models (DRMMs), a novel deep generative model architecture. Compared to other deep models, DRMMs allow more flexible conditional sampling: The model can be trained once with all variables, and then used for…

Machine Learning · Computer Science 2021-07-22 Perttu Hämäläinen , Martin Trapp , Tuure Saloheimo , Arno Solin

Data representation techniques have made a substantial contribution to advancing data processing and machine learning (ML). Improving predictive power was the focus of previous representation techniques, which unfortunately perform rather…

Machine Learning · Computer Science 2022-05-24 Qiyou Duan , Hadi Ghauch , Taejoon Kim

This paper studies the generalization performance of iterates obtained by Gradient Descent (GD), Stochastic Gradient Descent (SGD) and their proximal variants in high-dimensional robust regression problems. The number of features is…

Statistics Theory · Mathematics 2024-11-05 Kai Tan , Pierre C. Bellec

Efficient and high-fidelity prior sampling and inversion for complex geological media is still a largely unsolved challenge. Here, we use a deep neural network of the variational autoencoder type to construct a parametric low-dimensional…

Machine Learning · Statistics 2017-10-26 Eric Laloy , Romain Hérault , John Lee , Diederik Jacques , Niklas Linde

Deep generative models such as Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Diffusion Models, and Transformers, have shown great promise in a variety of applications, including image and speech synthesis, natural…

Machine Learning · Computer Science 2025-11-18 Lyle Regenwetter , Akash Srivastava , Dan Gutfreund , Faez Ahmed

Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theory credits implicit regularization imposed by the choice of…

Machine Learning · Computer Science 2026-03-17 Jonathan Wenger , Beau Coker , Juraj Marusic , John P. Cunningham

Differentiable rendering aims to compute the derivative of the image rendering function with respect to the rendering parameters. This paper presents a novel algorithm for 6-DoF pose estimation through gradient-based optimization using a…

Computer Vision and Pattern Recognition · Computer Science 2022-12-27 Ramchander Rao Bhaskara , Roshan Thomas Eapen , Manoranjan Majji

The minibatch stochastic gradient descent method (SGD) is widely applied in deep learning due to its efficiency and scalability that enable training deep networks with a large volume of data. Particularly in the distributed setting, SGD is…

Machine Learning · Computer Science 2020-11-19 Qiwei Yuan , Weizhe Hua , Yi Zhou , Cunxi Yu

Doubly robust (DR) estimation is a crucial technique in causal inference and missing data problems. We propose a novel Propensity score Augmentved Doubly robust (PAD) estimator to enhance the commonly used DR estimator for average treatment…

Methodology · Statistics 2023-04-18 Liangbo Lyu , Molei Liu

Overparameterized neural networks can be highly accurate on average on an i.i.d. test set yet consistently fail on atypical groups of the data (e.g., by learning spurious correlations that hold on average but not in such groups).…

Machine Learning · Computer Science 2020-04-03 Shiori Sagawa , Pang Wei Koh , Tatsunori B. Hashimoto , Percy Liang

A new type of robust estimation problem is introduced where the goal is to recover a statistical model that has been corrupted after it has been estimated from data. Methods are proposed for "repairing" the model using only the design and…

Statistics Theory · Mathematics 2020-05-21 Chao Gao , John Lafferty

Generative state estimators based on probabilistic filters and smoothers are one of the most popular classes of state estimators for robots and autonomous vehicles. However, generative models have limited capacity to handle rich sensory…

Machine Learning · Computer Science 2017-10-03 Tuomas Haarnoja , Anurag Ajay , Sergey Levine , Pieter Abbeel

In this work, we address a foundational question in the theoretical analysis of the Deep Ritz Method (DRM) under the over-parameteriztion regime: Given a target precision level, how can one determine the appropriate number of training…

Numerical Analysis · Mathematics 2024-07-15 Yuling Jiao , Ruoxuan Li , Peiying Wu , Jerry Zhijian Yang , Pingwen Zhang

In neural networks with binary activations and or binary weights the training by gradient descent is complicated as the model has piecewise constant response. We consider stochastic binary networks, obtained by adding noises in front of…

Machine Learning · Statistics 2020-11-05 Alexander Shekhovtsov , Viktor Yanush , Boris Flach

Deep reinforcement learning (DRL) on Markov decision processes (MDPs) with continuous action spaces is often approached by directly training parametric policies along the direction of estimated policy gradients (PGs). Previous research…

Machine Learning · Computer Science 2020-05-05 Gang Chen

Generalized Advantage Estimation (GAE) has been used to mitigate the computational complexity of reinforcement learning (RL) by employing an exponentially weighted estimation of the advantage function to reduce the variance in policy…

Machine Learning · Computer Science 2025-07-24 Shahil Shaik , Jonathon M. Smereka , Yue Wang

The advantage of using a Discrete Variable Representation (DVR) is that the Hamiltonian of two interacting particles can be constructed in a very simple form. However the DVR Hamiltonian is approximate and, as a consequence, the results…

Atomic and Molecular Clusters · Physics 2016-09-08 M. Lombardi , P. Barletta , A. Kievsky

Deterministic Rank Reduction Autoencoders (RRAEs) enforce by construction a regularization on the latent space by applying a truncated SVD. While this regularization makes Autoencoders more powerful, using them for generative purposes is…

Machine Learning · Computer Science 2025-10-15 Jad Mounayer , Alicia Tierz , Jerome Tomezyk , Chady Ghnatios , Francisco Chinesta

An ensemble method is introduced that utilizes randomization and loss function gradients to compute a prediction. Multiple weakly-correlated estimators approximate the gradient at randomly sampled points on the error surface and are…

Machine Learning · Computer Science 2020-09-15 Nicholas Smith
‹ Prev 1 4 5 6 7 8 10 Next ›