Tuning-Free Sampling via Optimization on the Space of Probability Measures
We introduce adaptive, tuning-free step size schedules for gradient-based sampling algorithms obtained as time-discretizations of Wasserstein gradient flows. The result is a suite of tuning-free sampling algorithms, including tuning-free variants of the unadjusted Langevin algorithm (ULA), stochastic gradient Langevin dynamics (SGLD), mean-field Langevin dynamics (MFLD), Stein variational gradient descent (SVGD), and variational gradient descent (VGD). More widely, our approach yields tuning-free algorithms for solving a broad class of stochastic optimization problems over the space of probability measures. Under mild assumptions (e.g., geodesic convexity and locally bounded stochastic gradients), we establish strong theoretical guarantees for our approach. In particular, we recover the convergence rate of optimally tuned versions of these algorithms up to logarithmic factors, in both nonsmooth and smooth settings. We then benchmark the performance of our methods against comparable existing approaches. Across a variety of tasks, our algorithms achieve similar performance to the optimal performance of existing algorithms, with no need to tune a step size parameter.
Code (0)
등록된 구현이 없습니다.
Tasks
Stochastic OptimizationSimilar Papers 제목 키워드 기반
Thompson Sampling via Fine-Tuning of LLMs
Bayesian optimization in large unstructured discrete spaces is often hindered by the computational cost of maximizing acquisition functions due to the absence of gradients. We propose a scalable alternative based on Thom…
Computational EfficiencyReinforcement LearningTuning-Free Stochastic Optimization
Large-scale machine learning problems make the cost of hyperparameter tuning ever more prohibitive. This creates a need for algorithms that can tune themselves on-the-fly. We formalize the notion of "tuning-free" algorit…
Stochastic OptimizationConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
Zeroth-order or derivative-free optimization (MeZO) is an attractive strategy for finetuning large language models (LLMs) because it eliminates the memory overhead of backpropagation. However, it converges slowly due to …
Latent Variables on Spheres for Sampling and Inference
Variational inference is a fundamental problem in Variational AutoEncoder (VAE). The optimization with lower bound of marginal log-likelihood results in the distribution of latent variables approximate to a given prior p…
Variational InferenceA Sampling-Free Approximation of Gaussian Variational Auto-Encoders
We propose a sampling-free approximate formulation of Gaussian variational auto-encoders. Instead of computing the loss via stochastic sampling, we propagate the Gaussian distributions from the latent space into the outp…
Decoder