English
Related papers

Related papers: On Divergence Measures for Training GFlowNets

200 papers

Optimum designs for parameter estimation in generalized regression models are standardly based on the Fisher information matrix (cf. Atkinson et al (2014) for a recent exposition). The corresponding optimality criteria are related to the…

Statistics Theory · Mathematics 2015-07-28 Katarína Burclová , Andrej Pázman

Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits tractable querying of this knowledge to start-to-end autoregressive sampling. However, many…

Machine Learning · Computer Science 2024-03-15 Edward J. Hu , Moksh Jain , Eric Elmoznino , Younesse Kaddar , Guillaume Lajoie , Yoshua Bengio , Nikolay Malkin

Recent network pruning methods focus on pruning models early-on in training. To estimate the impact of removing a parameter, these methods use importance measures that were originally designed to prune trained models. Despite lacking…

Machine Learning · Computer Science 2021-09-24 Ekdeep Singh Lubana , Robert P. Dick

Flow-based generative models leverage invertible generator functions to fit a distribution to the training data using maximum likelihood. Despite their use in several application domains, robustness of these models to adversarial attacks…

Machine Learning · Computer Science 2019-11-21 Phillip Pope , Yogesh Balaji , Soheil Feizi

Aligning language models with preferences can be posed as approximating a target distribution representing some desired behavior. Existing approaches differ both in the functional form of the target distribution and the algorithm used to…

Computation and Language · Computer Science 2023-06-07 Dongyoung Go , Tomasz Korbak , Germán Kruszewski , Jos Rozen , Nahyeon Ryu , Marc Dymetman

Diffusion models have emerged as a powerful paradigm for modern generative modeling, demonstrating strong potential for large language models (LLMs). Unlike conventional autoregressive (AR) models that generate tokens sequentially,…

Machine Learning · Computer Science 2026-01-09 Gen Li , Changxiao Cai

Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs). Contrary to prior assertions that reverse Kullback-Leibler (RKL) divergence is mode-seeking and thus preferable over…

Computation and Language · Computer Science 2024-12-10 Taiqiang Wu , Chaofan Tao , Jiahao Wang , Runming Yang , Zhe Zhao , Ngai Wong

Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combinatorial Optimization. Currently, popular deep learning-based…

Machine Learning · Computer Science 2025-08-25 Sebastian Sanokowski , Sepp Hochreiter , Sebastian Lehner

We consider the problem of sampling from a discrete and structured distribution as a sequential decision problem, where the objective is to find a stochastic policy such that objects are sampled at the end of this sequential process…

Machine Learning · Computer Science 2024-05-29 Tristan Deleu , Padideh Nouri , Nikolay Malkin , Doina Precup , Yoshua Bengio

Generative adversarial networks are a novel method for statistical inference that have achieved much empirical success; however, the factors contributing to this success remain ill-understood. In this work, we attempt to analyze generative…

Machine Learning · Computer Science 2018-09-13 Shuang Liu , Kamalika Chaudhuri

Neural Network (Deep Learning) is a modern model in Artificial Intelligence and it has been exploited in Survival Analysis. Although several improvements have been shown by previous works, training an excellent deep learning model requires…

Machine Learning · Statistics 2023-04-14 Li Liu , Xiangeng Fang , Di Wang , Weijing Tang , Kevin He

In this paper, we present gfnx, a fast and scalable package for training and evaluating Generative Flow Networks (GFlowNets) written in JAX. gfnx provides an extensive set of environments and metrics for benchmarking, accompanied with…

Machine Learning · Computer Science 2025-11-21 Daniil Tiapkin , Artem Agarkov , Nikita Morozov , Ian Maksimov , Askar Tsyganov , Timofei Gritsaev , Sergey Samsonov

Traditional generative adversarial networks (GAN) and many of its variants are trained by minimizing the KL or JS-divergence loss that measures how close the generated data distribution is from the true data distribution. A recent advance…

Computer Vision and Pattern Recognition · Computer Science 2017-04-18 Felix Juefei-Xu , Vishnu Naresh Boddeti , Marios Savvides

We provide a theoretical analysis for end-to-end training Discrete Flow Matching (DFM) generative models. DFM is a promising discrete generative modeling framework that learns the underlying generative dynamics by training a neural network…

Machine Learning · Computer Science 2025-09-29 Maojiang Su , Mingcheng Lu , Jerry Yao-Chieh Hu , Shang Wu , Zhao Song , Alex Reneau , Han Liu

Flow-matching models provide a powerful framework for various applications, offering efficient sampling and flexible probability path modeling. These models are characterized by flows with low curvature in learned generative trajectories,…

Machine Learning · Computer Science 2025-01-22 Zibin Wang , Zhiyuan Ouyang , Xiangyun Zhang

Personalized recommender systems fulfill the daily demands of customers and boost online businesses. The goal is to learn a policy that can generate a list of items that matches the user's demand or interest. While most existing methods…

Information Retrieval · Computer Science 2023-06-12 Shuchang Liu , Qingpeng Cai , Zhankui He , Bowen Sun , Julian McAuley , Dong Zheng , Peng Jiang , Kun Gai

We consider a distributed learning setup where a network of agents sequentially access realizations of a set of random variables with unknown distributions. The network objective is to find a parametrized distribution that best describes…

Optimization and Control · Mathematics 2016-05-10 Angelia Nedić , Alex Olshevsky , César Uribe

An adaptive sampling approach for efficient detection of bifurcation boundaries in parametrized fluid flow problems is presented herein. The study extends the machine-learning approach of Silvester~(J. Comput. Phys., 553 (2026), 114743),…

Fluid Dynamics · Physics 2026-02-19 Anshima Singh , David J. Silvester

The prototypical network (ProtoNet) is a few-shot learning framework that performs metric learning and classification using the distance to prototype representations of each class. It has attracted a great deal of attention recently since…

Machine Learning · Computer Science 2020-09-29 Kei Mukaiyama , Issei Sato , Masashi Sugiyama

This work presents a distributed algorithm for nonlinear adaptive learning. In particular, a set of nodes obtain measurements, sequentially one per time step, which are related via a nonlinear function; their goal is to collectively…

Information Theory · Computer Science 2016-02-09 Symeon Chouvardas , Moez Draief