English
Related papers

Related papers: On the Variance of Unbiased Online Recurrent Optim…

200 papers

Several variants of recurrent neural networks (RNNs) with orthogonal or unitary recurrent matrices have recently been developed to mitigate the vanishing/exploding gradient problem and to model long-term dependencies of sequences. However,…

Machine Learning · Computer Science 2019-11-20 Kyle Helfrich , Qiang Ye

Retrieval-augmented models couple parametric predictors with non-parametric memories, but their use in streaming supervised learning with concept drift is not well understood. We study online classification in non-stationary environments…

Machine Learning · Computer Science 2025-12-03 Wenzhang Du

Interest in derivative-free optimization (DFO) and "evolutionary strategies" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they can match state of the art methods for policy optimization…

Gradient estimation -- approximating the gradient of an expectation with respect to the parameters of a distribution -- is central to the solution of many machine learning problems. However, when the distribution is discrete, most common…

Machine Learning · Statistics 2024-04-16 Jiaxin Shi , Yuhao Zhou , Jessica Hwang , Michalis K. Titsias , Lester Mackey

We investigate an extension of continuous online learning in recurrent neural network language models. The model keeps a separate vector representation of the current unit of text being processed and adaptively adjusts it after each…

Computation and Language · Computer Science 2017-03-07 Marek Rei

Recurrent neural networks (RNNs) are more suitable for learning non-linear dependencies in dynamical systems from observed time series data. In practice all the external variables driving such systems are not known a priori, especially in…

Machine Learning · Computer Science 2020-06-02 Mhlasakululeka Mvubu , Emmanuel Kabuga , Christian Plitz , Bubacarr Bah , Ronnie Becker , Hans Georg Zimmermann

One of the central goals of Recurrent Neural Networks (RNNs) is to learn long-term dependencies in sequential data. Nevertheless, the most popular training method, Truncated Backpropagation through Time (TBPTT), categorically forbids…

Machine Learning · Computer Science 2019-05-20 Frederik Benzing , Marcelo Matheus Gauy , Asier Mujika , Anders Martinsson , Angelika Steger

We consider the robust estimation of the parameters of multivariate Gaussian linear regression models. To this aim we consider robust version of the usual (Mahalanobis) least-square criterion, with or without Ridge regularization. We…

Statistics Theory · Mathematics 2025-10-13 Antoine Godichon-Baggioni , Stephane S. Robin , Laure Sansonnet

Offline-to-online reinforcement learning (RL), a framework that trains a policy with offline RL and then further fine-tunes it with online RL, has been considered a promising recipe for data-driven decision-making. While sensible, this…

Machine Learning · Computer Science 2024-08-28 Junsu Kim , Seohong Park , Sergey Levine

While Distributional Reinforcement Learning (DRL) methods have demonstrated strong performance in online settings, its success in offline scenarios remains limited. We hypothesize that a key limitation of existing offline DRL methods lies…

Machine Learning · Computer Science 2026-01-06 Ryo Iwaki , Takayuki Osogami

Recurrent neural networks (RNNs) are powerful models of sequential data. They have been successfully used in domains such as text and speech. However, RNNs are susceptible to overfitting; regularization is important. In this paper we…

Machine Learning · Statistics 2018-07-16 Adji B. Dieng , Rajesh Ranganath , Jaan Altosaar , David M. Blei

This paper investigates several aspects of training a RNN (recurrent neural network) that impact the objective and subjective quality of enhanced speech for real-time single-channel speech enhancement. Specifically, we focus on a RNN that…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-14 Yangyang Xia , Sebastian Braun , Chandan K. A. Reddy , Harishchandra Dubey , Ross Cutler , Ivan Tashev

Bilevel optimization (BLO) is a popular approach with many applications including hyperparameter optimization, neural architecture search, adversarial robustness and model-agnostic meta-learning. However, the approach suffers from time and…

Machine Learning · Computer Science 2021-06-08 Valerii Likhosherstov , Xingyou Song , Krzysztof Choromanski , Jared Davis , Adrian Weller

Distributionally robust optimization (DRO) problems are increasingly seen as a viable method to train machine learning models for improved model generalization. These min-max formulations, however, are more difficult to solve. We therefore…

Machine Learning · Statistics 2020-11-03 Soumyadip Ghosh , Mark Squillante , Ebisa Wollega

In distributed optimization, the practical problem-solving performance is essentially sensitive to algorithm selection, parameter setting, problem type and data pattern. Thus, it is often laborious to acquire a highly efficient method for a…

Optimization and Control · Mathematics 2024-01-04 Daokuan Zhu , Tianqi Xu , Jie Lu

This paper develops a flexible method for decreasing the variance of estimators for complex experiment effect metrics (e.g. ratio metrics) while retaining asymptotic unbiasedness. This method uses the auxiliary information about the…

Statistics Theory · Mathematics 2019-04-09 Reza Hosseini , Amir Najmi

Inverse optimization is a powerful paradigm for learning preferences and restrictions that explain the behavior of a decision maker, based on a set of external signal and the corresponding decision pairs. However, most inverse optimization…

Machine Learning · Computer Science 2018-11-05 Chaosheng Dong , Yiran Chen , Bo Zeng

We derive an unbiased estimator for expectations over discrete random variables based on sampling without replacement, which reduces variance as it avoids duplicate samples. We show that our estimator can be derived as the…

Machine Learning · Computer Science 2020-02-17 Wouter Kool , Herke van Hoof , Max Welling

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…

Computation and Language · Computer Science 2023-04-07 Jeremy Wilkerson

Time series forecasting plays a crucial role in contemporary engineering information systems for supporting decision-making across various industries, where Recurrent Neural Networks (RNNs) have been widely adopted due to their capability…

Machine Learning · Computer Science 2026-01-14 Xin Lai , Shiming Deng , Lu Yu , Yumin Lai , Shenghao Qiao , Xinze Zhang