paper-with-me

Papers

Bootstrap Your Flow

2021-11-22 · pproximateinference AABI Symposium 2022 2 · Laurence Illing Midgley, Vincent Stimper, Gregor N. C. Simm, José Miguel Hernández-Lobato

Normalizing flows are flexible, parameterized distributions that can be used to approximate expectations from intractable distributions via importance sampling. However, current flow-based approaches are limited on challenging targets where they either suffer from mode seeking behaviour or high variance in the training loss, or rely on samples from the target distribution, which may not be available. To address these challenges, we combine flows with annealed importance sampling (AIS), while using the $\alpha$-divergence as our objective, in a novel training procedure, FAB (Flow AIS Bootstrap). Thereby, the flow and AIS improve each other in a bootstrapping manner. We demonstrate that FAB can be used to produce accurate approximations to complex target distributions, including Boltzmann distributions, in problems where previous flow-based methods fail.

📄 PDF Abstract BibTeX arXiv:2111.11510

Code (1)

lollcat/FAB-2021 공식 구현 pytorch

Tasks

Normalising Flows

Similar Papers 제목 키워드 기반

Bootstrap Your Own Context Length

2024-12-25 · Liang Wang, Nan Yang, Xingxing Zhang, Xiaolong Huang 외

We introduce a bootstrapping approach to train long-context language models by exploiting their short-context capabilities only. Our method utilizes a simple agent workflow to synthesize diverse long-context instruction …

Language ModelingLanguage Modelling

Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching

2026-06-02 · Yoad Tewel, Yuval Atzmon, Gal Chechik, Lior Wolf arxiv

Modern generative models possess a deep understanding of visual content, yet training them for image editing typically requires massive datasets of paired examples. This limits scalability, especially for video editing w…

Image Editing

Bootstrap Your Own Variance

2023-12-06 · Polina Turishcheva, Jason Ramapuram, Sinead Williamson, Dan Busbridge 외

Understanding model uncertainty is important for many applications. We propose Bootstrap Your Own Variance (BYOV), combining Bootstrap Your Own Latent (BYOL), a negative-free Self-Supervised Learning (SSL) algorithm, wit…

Self-Supervised Learning

Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance

2023-10-16 · Jesse Zhang, Jiahui Zhang, Karl Pertsch, Ziyi Liu 외

We propose BOSS, an approach that automatically learns to solve new long-horizon, complex, and meaningful tasks by growing a learned skill library with minimal supervision. Prior work in reinforcement learning require ex…

Language ModelingLanguage ModellingLarge Language Model

Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning

2020-12-01 · NeurIPS 2020 12 · Jean-bastien Grill, Florian Strub, Florent Altché, Corentin Tallec 외

We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from …

Linear evaluationRepresentation LearningSelf-Supervised Learning