arXiv research

PCTS optimizes noisy, delayed, multi-fidelity feedbacks in black-box optimization.

We consider a covariate shift problem where one has access to several different training datasets for the same learning problem and a small validation set which possibly differs from all the individual training distributions. This covariate shift is caused, in part, due to unobserved features in the datasets. The objec…

Optimistic search speeds up change point detection in large datasets.

Bayesian optimisation (BO) is a well-known efficient algorithm for finding the global optimum of expensive, black-box functions. The current practical BO algorithms have regret bounds ranging from $\mathcal{O}(\frac{logN}{\sqrt{N}})$ to $\mathcal O(e^{-\sqrt{N}})$, where $N$ is the number of evaluations. This paper exp…

Bayesian classifier improves robustness with optimistic score ratio.

New method minimizes regret in AMDP with high probability.

Optimistic method adapted for faster convex-concave min-max problems.

Proposes H-UCRL for efficient model-based RL with sublinear regret.

A new algorithm, Regular Tree Search, tackles non-convex simulation optimization problems.

Paper uses CMAB to improve NAS efficiency and accuracy.

Monte Carlo Tree Search improves financial derivative hedging efficiency.

Optimizes tree models for better beam search performance.

Monte Carlo Tree Search (MCTS) algorithms perform simulation-based search to improve policies online. During search, the simulation policy is adapted to explore the most promising lines of play. MCTS has been used by state-of-the-art programs for many problems, however a disadvantage to MCTS is that it estimates the va…

We present an extension of Monte Carlo Tree Search (MCTS) that strongly increases its efficiency for trees with asymmetry and/or loops. Asymmetric termination of search trees introduces a type of uncertainty for which the standard upper confidence bound (UCB) formula does not account. Our first algorithm (MCTS-T), whic…

A generalized optimistic method for saddle point problems with improved complexity.

We consider the classical sparse regression problem of recovering a sparse signal $x_0$ given a measurement vector $y = Φx_0+w$. We propose a tree search algorithm driven by the deep neural network for sparse regression (TSN). TSN improves the signal reconstruction performance of the deep neural network designed for sp…

Accelerates policy optimization in RL with optimistic and adaptive updates.

Automates optimizer design for diverse tasks efficiently.

AlphaCFG discovers alpha factors using grammar-guided search.

Optimal decision trees learned via dynamic programming and search.

SMAC method optimizes tree-boosting hyperparameters best.

A hybrid model for Bayesian optimization handles mixed variables using MCTS for categorical and GP for continuous.

Transformer learns to search through reinforcement learning, mimicking DFS.

Planning problems are among the most important and well-studied problems in artificial intelligence. They are most typically solved by tree search algorithms that simulate ahead into the future, evaluate future states, and back-up those evaluations to the root of a search tree. Among these algorithms, Monte-Carlo tree …

A new algorithm improves sample complexity for thresholding in Monte Carlo Tree Search.

Finite-horizon lookahead policies are abundantly used in Reinforcement Learning and demonstrate impressive empirical success. Usually, the lookahead policies are implemented with specific planning methods such as Monte Carlo Tree Search (e.g. in AlphaZero). Referring to the planning problem as tree search, a reasonable…

This paper improves self-play learning in games by manipulating experience distributions.

DTS improves inference-time alignment of diffusion models with less compute.

Combines MCTS and neural networks for efficient multi-period financial planning.

Paper shows MCTS approximates policy optimization, proposing an improved variant.

New method learns better branching policies for MILP problems.

Predict accuracy of neural architectures using non-neural models.

The game of Chinese Checkers is a challenging traditional board game of perfect information that differs from other traditional games in two main aspects: first, unlike Chess, all checkers remain indefinitely in the game and hence the branching factor of the search tree does not decrease as the game progresses; second,…

SIREN protocol corrects optimistic winner's scores in LLM evaluation.

Decision trees are flexible models that are well suited for many statistical regression problems. In a Bayesian framework for regression trees, Markov Chain Monte Carlo (MCMC) search algorithms are required to generate samples of tree models according to their posterior probabilities. The critical component of such an …

Recent advances in bandit tools and techniques for sequential learning are steadily enabling new applications and are promising the resolution of a range of challenging related problems. We study the game tree search problem, where the goal is to quickly identify the optimal move in a given game tree by sequentially sa…

Improves diffusion model performance and efficiency through classical search.

Gradient-based methods are often used for policy optimization in deep reinforcement learning, despite being vulnerable to local optima and saddle points. Although gradient-free methods (e.g., genetic algorithms or evolution strategies) help mitigate these issues, poor initialization and local optima are still concerns …

LA-MCTS learns search space partition for black-box optimization using Monte Carlo Tree Search.

Bayesian methods improve drug discovery experiment design.

Approximate nearest neighbor algorithms are used to speed up nearest neighbor search in a wide array of applications. However, current indexing methods feature several hyperparameters that need to be tuned to reach an acceptable accuracy--speed trade-off. A grid search in the parameter space is often impractically slow…

We adopt data structure in the form of cover trees and iteratively apply approximate nearest neighbour (ANN) searches for fast compressed sensing reconstruction of signals living on discrete smooth manifolds. Levering on the recent stability results for the inexact Iterative Projected Gradient (IPG) algorithm and by us…

DR-MCTS improves decision quality and sample efficiency in complex environments.

Deep reinforcement learning has been successfully applied to several visual-input tasks using model-free methods. In this paper, we propose a model-based approach that combines learning a DNN-based transition model with Monte Carlo tree search to solve a block-placing task in Minecraft. Our learned transition model pre…

Tree ensemble kernels improve Bayesian optimization for mixed features and constraints.

Neural Architecture Search (NAS) has shown great success in automating the design of neural networks, but the prohibitive amount of computations behind current NAS methods requires further investigations in improving the sample efficiency and the network evaluation cost to get better results in a shorter time. In this …

Parallelizes MCTS for continuous domains using leaf and root parallelization.

Improves RL planning by proposing sub-goals hierarchically.