Debiased Distribution Compression

• URL: http://arxiv.org/abs/2404.12290v3
• Date: Wed, 31 Jul 2024 20:32:46 GMT
• Title: Debiased Distribution Compression
• Authors: Lingxiao Li, Raaz Dwivedi, Lester Mackey,
• Abstract summary: We introduce a new suite of compression methods suitable for compression with biased input sequences. We provide succinct and accurate posterior summaries while overcoming biases due to burn-in, approximate Markov chain Monte Carlo, and tempering.
• Score: 30.600795754425775
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern compression methods can summarize a target distribution $\mathbb{P}$ more succinctly than i.i.d. sampling but require access to a low-bias input sequence like a Markov chain converging quickly to $\mathbb{P}$. We introduce a new suite of compression methods suitable for compression with biased input sequences. Given $n$ points targeting the wrong distribution and quadratic time, Stein kernel thinning (SKT) returns $\sqrt{n}$ equal-weighted points with $\widetilde{O}(n^{-1/2})$ maximum mean discrepancy (MMD) to $\mathbb{P}$. For larger-scale compression tasks, low-rank SKT achieves the same feat in sub-quadratic time using an adaptive low-rank debiasing procedure that may be of independent interest. For downstream tasks that support simplex or constant-preserving weights, Stein recombination and Stein Cholesky achieve even greater parsimony, matching the guarantees of SKT with as few as $\text{poly-log}(n)$ weighted points. Underlying these advances are new guarantees for the quality of simplex-weighted coresets, the spectral decay of kernel matrices, and the covering numbers of Stein kernel Hilbert spaces. In our experiments, our techniques provide succinct and accurate posterior summaries while overcoming biases due to burn-in, approximate Markov chain Monte Carlo, and tempering.

Related papers

• Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling [28.931489333515618]
  We establish an oracle complexity of $widetildeOleft(fracdbeta2cal A2varepsilon6right)$ for simple annealed Langevin Monte Carlo algorithm. We show that $cal A$ represents the action of a curve of probability measures interpolating the target distribution $pi$ and a readily sampleable distribution.
  arXiv  Detail & Related papers  (2024-07-24T02:15:48Z)
• Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs [56.237917407785545]
  We consider the problem of learning an $varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Key to our solution is a novel projection technique based on ideas from harmonic analysis. Our result bridges the gap between two popular but conflicting perspectives on continuous-space MDPs.
  arXiv  Detail & Related papers  (2024-05-10T09:58:47Z)
• Minimal Random Code Learning with Mean-KL Parameterization [2.3814052021083354]
  We study two variants of Minimal Random Code Learning (MIRACLE) used to compress variational Bayesian neural networks. MIRACLE implements a powerful, conditionally Gaussian variational approximation for the weight posterior $Q_mathbfw$ and uses relative entropy coding to compress a weight sample from the posterior. We show that variational training with Mean-KL parameterization converges twice as fast and maintains predictive performance after compression.
  arXiv  Detail & Related papers  (2023-07-15T14:46:43Z)
• Settling the Sample Complexity of Model-Based Offline Reinforcement Learning [50.5790774201146]
  offline reinforcement learning (RL) learns using pre-collected data without further exploration. Prior algorithms or analyses either suffer from suboptimal sample complexities or incur high burn-in cost to reach sample optimality. We demonstrate that the model-based (or "plug-in") approach achieves minimax-optimal sample complexity without burn-in cost.
  arXiv  Detail & Related papers  (2022-04-11T17:26:19Z)
• A Law of Robustness beyond Isoperimetry [84.33752026418045]
  We prove a Lipschitzness lower bound $Omega(sqrtn/p)$ of robustness of interpolating neural network parameters on arbitrary distributions. We then show the potential benefit of overparametrization for smooth data when $n=mathrmpoly(d)$. We disprove the potential existence of an $O(1)$-Lipschitz robust interpolating function when $n=exp(omega(d))$.
  arXiv  Detail & Related papers  (2022-02-23T16:10:23Z)
• Distribution Compression in Near-linear Time [27.18971095426405]
  We introduce Compress++, a simple meta-procedure for speeding up any thinning algorithm. It delivers $sqrtn$ points with $mathcalO(sqrtlog n/n)$ integration error and better-than-Monte-Carlo maximum mean discrepancy.
  arXiv  Detail & Related papers  (2021-11-15T17:42:57Z)
• Linear Time Sinkhorn Divergences using Positive Features [51.50788603386766]
  Solving optimal transport with an entropic regularization requires computing a $ntimes n$ kernel matrix that is repeatedly applied to a vector. We propose to use instead ground costs of the form $c(x,y)=-logdotpvarphi(x)varphi(y)$ where $varphi$ is a map from the ground space onto the positive orthant $RRr_+$, with $rll n$.
  arXiv  Detail & Related papers  (2020-06-12T10:21:40Z)
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction [63.41789556777387]
  Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP) We show that the number of samples needed to yield an entrywise $varepsilon$-accurate estimate of the Q-function is at most on the order of $frac1mu_min (1-gamma)5varepsilon2+ fract_mixmu_min (1-gamma)$ up to some logarithmic factor.
  arXiv  Detail & Related papers  (2020-06-04T17:51:00Z)
• Robustly Learning any Clusterable Mixture of Gaussians [55.41573600814391]
  We study the efficient learnability of high-dimensional Gaussian mixtures in the adversarial-robust setting. We provide an algorithm that learns the components of an $epsilon$-corrupted $k$-mixture within information theoretically near-optimal error proofs of $tildeO(epsilon)$. Our main technical contribution is a new robust identifiability proof clusters from a Gaussian mixture, which can be captured by the constant-degree Sum of Squares proof system.
  arXiv  Detail & Related papers  (2020-05-13T16:44:12Z)
• Optimal Thinning of MCMC Output [18.177473712344565]
  We consider the problem of retrospectively selecting a subset of states, of fixed cardinality, from the sample path. A novel method is proposed, based on greedy minimisation of a kernel discrepancy, that is suitable for problems where heavy compression is required.
  arXiv  Detail & Related papers  (2020-05-08T10:54:25Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.