Related papers: Implicit Diffusion: Efficient Optimization through Stochastic Sampling

Implicit Diffusion: Efficient Optimization through Stochastic Sampling

URL: http://arxiv.org/abs/2402.05468v2
Date: Wed, 22 May 2024 13:22:31 GMT
Title: Implicit Diffusion: Efficient Optimization through Stochastic Sampling
Authors: Pierre Marion, Anna Korba, Peter Bartlett, Mathieu Blondel, Valentin De Bortoli, Arnaud Doucet, Felipe Llinares-López, Courtney Paquette, Quentin Berthet,
Abstract summary: We present a new algorithm to optimize distributions defined implicitly by parameterized diffusions. We introduce a general framework for first-order optimization of these processes, that performs jointly. We apply it to training energy-based models and finetuning denoising diffusions.
Score: 46.049117719591635
License: http://creativecommons.org/licenses/by-sa/4.0/
Abstract: We present a new algorithm to optimize distributions defined implicitly by parameterized stochastic diffusions. Doing so allows us to modify the outcome distribution of sampling processes by optimizing over their parameters. We introduce a general framework for first-order optimization of these processes, that performs jointly, in a single loop, optimization and sampling steps. This approach is inspired by recent advances in bilevel optimization and automatic implicit differentiation, leveraging the point of view of sampling as optimization over the space of probability distributions. We provide theoretical guarantees on the performance of our method, as well as experimental results demonstrating its effectiveness. We apply it to training energy-based models and finetuning denoising diffusions.

Related papers

Sample-efficient Bayesian Optimisation Using Known Invariances [56.34916328814857]
We show that vanilla and constrained BO algorithms are inefficient when optimising invariant objectives. We derive a bound on the maximum information gain of these invariant kernels. We use our method to design a current drive system for a nuclear fusion reactor, finding a high-performance solution.
arXiv Detail & Related papers (2024-10-22T12:51:46Z)
Dynamic Anisotropic Smoothing for Noisy Derivative-Free Optimization [0.0]
We propose a novel algorithm that extends the methods of ball smoothing and Gaussian smoothing for noisy derivative-free optimization. The algorithm dynamically adapts the shape of the smoothing kernel to approximate the Hessian of the objective function around a local optimum.
arXiv Detail & Related papers (2024-05-02T21:04:20Z)
Enhancing Gaussian Process Surrogates for Optimization and Posterior Approximation via Random Exploration [2.984929040246293]
novel noise-free Bayesian optimization strategies that rely on a random exploration step to enhance the accuracy of Gaussian process surrogate models. New algorithms retain the ease of implementation of the classical GP-UCB, but an additional exploration step facilitates their convergence.
arXiv Detail & Related papers (2024-01-30T14:16:06Z)
Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers [143.6249073384419]
In this paper, we propose a distributed sampling scheme based on the alternating direction method of multipliers. We provide both theoretical guarantees of our algorithm's convergence and experimental evidence of its superiority to the state-of-the-art. In simulation, we deploy our algorithm on linear and logistic regression tasks and illustrate its fast convergence compared to existing gradient-based methods.
arXiv Detail & Related papers (2024-01-29T02:08:40Z)
Optimal Budgeted Rejection Sampling for Generative Models [54.050498411883495]
Rejection sampling methods have been proposed to improve the performance of discriminator-based generative models. We first propose an Optimal Budgeted Rejection Sampling scheme that is provably optimal. Second, we propose an end-to-end method that incorporates the sampling scheme into the training procedure to further enhance the model's overall performance.
arXiv Detail & Related papers (2023-11-01T11:52:41Z)
Minibatch and Momentum Model-based Methods for Stochastic Non-smooth Non-convex Optimization [3.4809730725241597]
We make two important extensions to model-based methods. First, we propose a new minibatch which takes a set of samples to approximate the model function in each iteration. Second, by the success of momentum techniques we propose a new convex-based model.
arXiv Detail & Related papers (2021-06-06T05:31:57Z)
Robust, Accurate Stochastic Optimization for Variational Inference [68.83746081733464]
We show that common optimization methods lead to poor variational approximations if the problem is moderately large. Motivated by these findings, we develop a more robust and accurate optimization framework by viewing the underlying algorithm as producing a Markov chain.
arXiv Detail & Related papers (2020-09-01T19:12:11Z)
BOSH: Bayesian Optimization by Sampling Hierarchically [10.10241176664951]
We propose a novel BO routine pairing a hierarchical Gaussian process with an information-theoretic framework to generate a growing pool of realizations. We demonstrate that BOSH provides more efficient and higher-precision optimization than standard BO across synthetic benchmarks, simulation optimization, reinforcement learning and hyper- parameter tuning tasks.
arXiv Detail & Related papers (2020-07-02T07:35:49Z)
Distributed Averaging Methods for Randomized Second Order Optimization [54.51566432934556]
We consider distributed optimization problems where forming the Hessian is computationally challenging and communication is a bottleneck. We develop unbiased parameter averaging methods for randomized second order optimization that employ sampling and sketching of the Hessian. We also extend the framework of second order averaging methods to introduce an unbiased distributed optimization framework for heterogeneous computing systems.
arXiv Detail & Related papers (2020-02-16T09:01:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.