English
Related papers

Related papers: Gradient Variance Reveals Failure Modes in Flow-Ba…

200 papers

A major obstacle to developing artificial intelligence applications capable of true lifelong learning is that artificial neural networks quickly or catastrophically forget previously learned tasks when trained on a new one. Numerous methods…

Machine Learning · Computer Science 2019-04-18 Gido M. van de Ven , Andreas S. Tolias

The Generative Flow Network is a probabilistic framework where an agent learns a stochastic policy for object generation, such that the probability of generating an object is proportional to a given reward function. Its effectiveness has…

Machine Learning · Computer Science 2022-10-10 Ling Pan , Dinghuai Zhang , Aaron Courville , Longbo Huang , Yoshua Bengio

Variational inference is a technique that approximates a target distribution by optimizing within the parameter space of variational families. On the other hand, Wasserstein gradient flows describe optimization within the space of…

Machine Learning · Statistics 2023-11-01 Mingxuan Yi , Song Liu

We study the approximation capabilities, convergence speeds and on-convergence behaviors of transformers trained on in-context recall tasks -- which requires to recognize the \emph{positional} association between a pair of tokens from…

Machine Learning · Computer Science 2025-10-22 Quan Nguyen , Thanh Nguyen-Tang

Interpreting gradient methods as fixed-point iterations, we provide a detailed analysis of those methods for minimizing convex objective functions. Due to their conceptual and algorithmic simplicity, gradient methods are widely used in…

Machine Learning · Statistics 2017-08-16 Alexander Jung

The unsupervised task of aligning two or more distributions in a shared latent space has many applications including fair representations, batch effect mitigation, and unsupervised domain adaptation. Existing flow-based approaches estimate…

Machine Learning · Computer Science 2022-03-17 Zeyu Zhou , Ziyu Gong , Pradeep Ravikumar , David I. Inouye

Auto-encoding generative adversarial networks (GANs) combine the standard GAN algorithm, which discriminates between real and model-generated data, with a reconstruction loss given by an auto-encoder. Such models aim to prevent mode…

Machine Learning · Statistics 2017-10-24 Mihaela Rosca , Balaji Lakshminarayanan , David Warde-Farley , Shakir Mohamed

High-dimensional integration with respect to complex target measures remains a fundamental challenge in computational science. While Flow Matching (FM) offers a powerful paradigm for constructing continuous-time transport maps, its…

Numerical Analysis · Mathematics 2026-01-06 Zhijun Zeng , Jianlong Chen

It is crucial to ask how agents can achieve goals by generating action plans using only partial models of the world acquired through habituated sensory-motor experiences. Although many existing robotics studies use a forward model…

Robotics · Computer Science 2020-06-01 Takazumi Matsumoto , Jun Tani

Diffusion-based generative models learn to iteratively transfer unstructured noise to a complex target distribution as opposed to Generative Adversarial Networks (GANs) or the decoder of Variational Autoencoders (VAEs) which produce samples…

Machine Learning · Computer Science 2022-10-26 Sarthak Mittal , Guillaume Lajoie , Stefan Bauer , Arash Mehrjou

We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the dataset in offline RL or the base model in LLM RL finetuning) is essential to prevent value over-optimization caused by…

Machine Learning · Computer Science 2026-04-17 Haoran Xu , Kaiwen Hu , Somayeh Sojoudi , Amy Zhang

We tackle the problem of sampling from intractable high-dimensional density functions, a fundamental task that often appears in machine learning and statistics. We extend recent sampling-based approaches that leverage controlled stochastic…

Machine Learning · Computer Science 2024-03-12 Dinghuai Zhang , Ricky T. Q. Chen , Cheng-Hao Liu , Aaron Courville , Yoshua Bengio

Matching objectives underpin the success of modern generative models and rely on constructing conditional paths that transform a source distribution into a target distribution. Despite being a fundamental building block, conditional paths…

High-dimensional generative modeling is fundamentally a manifold-learning problem: real data concentrate near a low-dimensional structure embedded in the ambient space. Effective generators must therefore balance support fidelity -- placing…

Machine Learning · Statistics 2026-02-24 Xinyu Tian , Xiaotong Shen

Guidance of generative models is typically achieved by modifying the probability flow vector field through the addition of a guidance field. In this paper, we instead propose the Source-Guided Flow Matching (SGFM) framework, which modifies…

Machine Learning · Computer Science 2025-08-25 Zifan Wang , Alice Harting , Matthieu Barreau , Michael M. Zavlanos , Karl H. Johansson

Neural operators are promising surrogates for dynamical systems but when trained with standard L2 losses they tend to oversmooth fine-scale turbulent structures. Here, we show that combining operator learning with generative modeling…

Flow matching has recently emerged as a powerful alternative to diffusion models, providing a continuous-time formulation for generative modeling and representation learning. Yet, we show that this framework suffers from a fundamental…

Machine Learning · Computer Science 2025-09-26 Weili Zeng , Yichao Yan

Flow-based models are powerful tools for designing probabilistic models with tractable density. This paper introduces Convex Potential Flows (CP-Flow), a natural and efficient parameterization of invertible models inspired by the optimal…

Machine Learning · Computer Science 2021-02-25 Chin-Wei Huang , Ricky T. Q. Chen , Christos Tsirigotis , Aaron Courville

Many modern learning tasks involve fitting nonlinear models to data which are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Due to this overparameterization, the training…

Machine Learning · Computer Science 2018-12-27 Samet Oymak , Mahdi Soltanolkotabi

We present a hybrid transformer architecture that replaces discrete middle layers with a continuous-depth Neural Ordinary Differential Equation (ODE) block, enabling inference-time control over generation attributes via a learned steering…

Machine Learning · Computer Science 2026-01-16 Peter Jemley
‹ Prev 1 8 9 10 Next ›