English
Related papers

Related papers: Measure-conditional Discriminator with Stationary …

200 papers

We propose a framework for adversarial training that relies on a sample rather than a single sample point as the fundamental unit of discrimination. Inspired by discrepancy measures and two-sample tests between probability distributions, we…

Machine Learning · Computer Science 2017-07-11 Chengtao Li , David Alvarez-Melis , Keyulu Xu , Stefanie Jegelka , Suvrit Sra

Matching the performance of conditional Generative Adversarial Networks with little supervision is an important task, especially in venturing into new domains. We design a new training algorithm, which is robust to missing or ambiguous…

Machine Learning · Statistics 2019-06-11 Kiran Koshy Thekumparampil , Sewoong Oh , Ashish Khetan

Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance…

Machine Learning · Computer Science 2019-09-25 Gregory Farquhar , Shimon Whiteson , Jakob Foerster

Deep generative models with latent variables have been used lately to learn joint representations and generative processes from multi-modal data. These two learning mechanisms can, however, conflict with each other and representations can…

Machine Learning · Computer Science 2023-01-24 Rogelio A. Mancisidor , Michael Kampffmeyer , Kjersti Aas , Robert Jenssen

Computing cross-partial derivatives using fewer model runs is relevant in modeling, such as stochastic approximation, derivative-based ANOVA, exploring complex models, and active subspaces. This paper introduces surrogates of all the…

Methodology · Statistics 2024-07-17 Matieyendou Lamboni

Adaptation of a classifier to new domains is one of the challenging problems in machine learning. This has been addressed using many deep and non-deep learning based methods. Among the methodologies used, that of adversarial learning is…

Machine Learning · Computer Science 2021-07-12 Vinod K Kurmi , Venkatesh K Subramanian , Vinay P. Namboodiri

We study a class of distribution-steering problems from a variational point of view. Under some differentiability assumptions, we derive necessary conditions for optimal Markov policies in the spirit of the Lagrange multiplier approach. We…

Optimization and Control · Mathematics 2025-08-29 Alberto Domínguez Corella , David González-Sánchez

Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs.…

Machine Learning · Computer Science 2023-12-29 Liang Hou , Qi Cao , Yige Yuan , Songtao Zhao , Chongyang Ma , Siyuan Pan , Pengfei Wan , Zhongyuan Wang , Huawei Shen , Xueqi Cheng

Pre-training Transformer models is resource-intensive, and recent studies have shown that sign momentum is an efficient technique for training large-scale deep learning models, particularly Transformers. However, its application in…

Machine Learning · Computer Science 2025-03-11 Shuhua Yu , Ding Zhou , Cong Xie , An Xu , Zhi Zhang , Xin Liu , Soummya Kar

Recent works propose using the discriminator of a GAN to filter out unrealistic samples of the generator. We generalize these ideas by introducing the implicit Metropolis-Hastings algorithm. For any implicit probabilistic model and a target…

Machine Learning · Statistics 2019-06-11 Kirill Neklyudov , Evgenii Egorov , Dmitry Vetrov

Generative Adversarial Networks (GANs) are powerful models able to synthesize data samples closely resembling the distribution of real data, yet the diversity of those generated samples is limited due to the so-called mode collapse…

Computer Vision and Pattern Recognition · Computer Science 2023-06-26 Jan Dubiński , Kamil Deja , Sandro Wenzel , Przemysław Rokita , Tomasz Trzciński

We show that an optimality condition of M-stationarity type holds for minimizers of a class of mathematical programs with complementarity constraints (MPCCs) in Lebesgue spaces. We apply these results also to local minimizers of an inverse…

Optimization and Control · Mathematics 2021-10-25 Felix Harder , Gerd Wachsmuth

We construct several variational integrators--integrators based on a discrete variational principle--for systems with Lagrangians of the form L = L_A + epsilon L_B, with epsilon << 1, where L_A describes an integrable system. These…

Astrophysics · Physics 2009-01-25 Will M. Farr

Generative adversarial networks (GANs) are a learning framework that rely on training a discriminator to estimate a measure of difference between a target and generated distributions. GANs, as normally formulated, rely on the generated…

Machine Learning · Statistics 2018-02-23 R Devon Hjelm , Athul Paul Jacob , Tong Che , Adam Trischler , Kyunghyun Cho , Yoshua Bengio

Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes…

Computer Vision and Pattern Recognition · Computer Science 2020-10-08 Tero Karras , Miika Aittala , Janne Hellsten , Samuli Laine , Jaakko Lehtinen , Timo Aila

In policy learning, the goal is typically to optimize a primary performance metric, but other subsidiary metrics often also warrant attention. This paper presents two strategies for evaluating these subsidiary metrics under a policy that is…

Statistics Theory · Mathematics 2025-09-09 Zhaoqi Li , Houssam Nassif , Alex Luedtke

Measurement-constrained datasets, often encountered in semi-supervised learning, arise when data labeling is costly, time-intensive, or hindered by confidentiality or ethical concerns, resulting in a scarcity of labeled data. In certain…

Methodology · Statistics 2025-01-15 Yixin Shen , Yang Ning

Recommendation techniques are important approaches for alleviating information overload. Being often trained on implicit user feedback, many recommenders suffer from the sparsity challenge due to the lack of explicitly negative samples. The…

Information Retrieval · Computer Science 2020-11-03 Binbin Jin , Defu Lian , Zheng Liu , Qi Liu , Jianhui Ma , Xing Xie , Enhong Chen

The main purpose of this paper is to introduce and study the behavior of minimum {\phi}-divergence estimators as an alternative to the maximum likelihood estimator in latent class models for binary items. As it will become clear below,…

Methodology · Statistics 2014-06-03 Ángel Felipe , Pedro Miranda , Leandro Pardo

Reinforcement learning methods for robotics are increasingly successful due to the constant development of better policy gradient techniques. A precise (low variance) and accurate (low bias) gradient estimator is crucial to face…

Machine Learning · Computer Science 2021-07-21 João Carvalho , Davide Tateo , Fabio Muratore , Jan Peters