arXiv research

Proposes r2SGLD for efficient constrained exploration in non-convex learning.

The area of constrained clustering has been extensively explored by researchers and used by practitioners. Constrained clustering formulations exist for popular algorithms such as k-means, mixture models, and spectral clustering but have several limitations. A fundamental strength of deep learning is its flexibility, a…

LCBO tackles constrained optimization in high dimensions, offering a polynomial convergence rate.

Study uses RL to optimize investment with financial constraints, showing exploration benefits.

Algorithm optimizes a single attribute in multi-armed bandits with constraints.

Paper proposes CVaR-TS for risk-constrained MAB problems.

Adapts Bayesian optimization for mixed constraints in aircraft design.

The present work extends the randomized shortest-paths framework (RSP), interpolating between shortest-path and random-walk routing in a network, in three directions. First, it shows how to deal with equality constraints on a subset of transition probabilities and develops a generic algorithm for solving this constrain…

VaR-CPO optimizes VaR-constrained RL problems with conservative policy updates.

We find the optimal error for a constrained regression model under a linear model.

The paper analyzes constrained optimal portfolios in high dimensions using novel statistical learning techniques.

Interactive Fiction games are text-based simulations in which an agent interacts with the world purely through natural language. They are ideal environments for studying how to extend reinforcement learning agents to meet the challenges of natural language understanding, partial observability, and action generation in …

Efficient method for constrained optimization under partial observations with provable convergence.

This work compares regularization and constrained inference for label constraints in machine learning.

The paper analyzes CMDPs, balancing exploration and exploitation to avoid constraint violations.

Algorithm optimizes constrained reinforcement learning with dual variables.

The paper explores solving inverse problems for ODEs with and without constraints.

We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques. We present a framework which allows for system identification through persistent excitation, while maintaining safety by guaranteeing the satisfaction of st…

Bayesian optimization tackles constrained high-dimensional problems with penalties and trust regions.

Energy savings for DNN inference on resource-constrained devices.

A bandit algorithm reduces regret in noisy, communication-constrained feedback.

New method optimizes processes under constraints using bivariate Gaussian models.

The paper explores invariant subbundles in nonholonomic mechanics.

State-constrained offline RL expands RL's learning scope.

New model generates data on constrained sets without losing tractability.

Kernel ridge regression is used to approximate the kinetic energy of non-interacting fermions in a one-dimensional box as a functional of their density. The properties of different kernels and methods of cross-validation are explored, and highly accurate energies are achieved. Accurate {\em constrained optimal densitie…

Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an agent in a constrained environment to concurrently reason about both its internal …

Study examines sample complexity for RL with safety constraints.

Proposes a new Lasso method with performance constraints.

Revel tackles safe exploration in RL with verified symbolic policies.

Constrained Markov Decision Processes are a class of stochastic decision problems in which the decision maker must select a policy that satisfies auxiliary cost constraints. This paper extends upper confidence reinforcement learning for settings in which the reward function and the constraints, described by cost functi…

BanditLP optimizes personalized recommendations for large-scale systems.

Machine learning algorithms generally suffer from a problem of explainability. Given a classification result from a model, it is typically hard to determine what caused the decision to be made, and to give an informative explanation. We explore a new method of generating counterfactual explanations, which instead of ex…

Choquet regularization improves exploration in RL.

We study contextual bandits with budget and time constraints, referred to as constrained contextual bandits.The time and budget constraints significantly complicate the exploration and exploitation tradeoff because they introduce complex coupling among contexts over time.Such coupling effects make it difficult to obtai…

ACE improves GFlowNet exploration efficiency by balancing complementary search strategies.

New method avoids failures in physics-constrained systems using active learning.

Latent class model (LCM), which is a finite mixture of different categorical distributions, is one of the most widely used models in statistics and machine learning fields. Because of its non-continuous nature and the flexibility in shape, researchers in practice areas such as marketing and social sciences also frequen…

New RL approach tackles constrained Markov decision processes.

Safe RL in linear systems achieves $\sqrt{T}$-regret.

Stochastic bridges are commonly used to impute missing data with a lower sampling rate to generate data with a higher sampling rate, while preserving key properties of the dynamics involved in an unbiased way. While the generation of Brownian bridges and Ornstein-Uhlenbeck bridges is well understood, unbiased generatio…

Enhanced PC$^2$ improves surrogate modeling for high-dimensional problems.

Social trust prediction addresses the significant problem of exploring interactions among users in social networks. Naturally, this problem can be formulated in the matrix completion framework, with each entry indicating the trustness or distrustness. However, there are two challenges for the social trust problem: 1) t…

The outcome of the explorative data analysis (EDA) phase is vital for successful data analysis. EDA is more effective when the user interacts with the system used to carry out the exploration. In the recently proposed paradigm of iterative data mining the user controls the exploration by inputting knowledge in the form…

Efficient explorative data analysis systems must take into account both what a user knows and wants to know. This paper proposes a principled framework for interactive visual exploration of relations in data, through views most informative given the user's current knowledge and objectives. The user can input pre-existi…

Paper tackles efficient navigation in constrained environments using supervised and reinforcement learning.

This paper presents a distributionally robust Q-Learning algorithm (DrQ) which leverages Wasserstein ambiguity sets to provide idealistic probabilistic out-of-sample safety guarantees during online learning. First, we follow past work by separating the constraint functions from the principal objective to create a hiera…

Safe RL for autonomous vehicles using PCPO with trust regions and parallel learners.