arXiv research

CoCoRL learns safe constraints from demonstrations with unknown rewards.

Study on neural networks to identify redundancy issues in safe machine learning.

Safe linear stochastic bandits ensure safe exploration with optimal regret.

Safe learning of stochastic dynamics with safety constraints.

We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made between the probability of following the optimal policy in the limit, and the probability of escaping a dangerous situation created by the adve…

New algorithm for safe bandits with unknown parameters and constraints.

Meta-learning priors improves safe Bayesian optimization.

We study the problem of safe learning and exploration in sequential control problems. The goal is to safely collect data samples from operating in an environment, in order to learn to achieve a challenging control goal (e.g., an agile maneuver close to a boundary). A central challenge in this setting is how to quantify…

We study safe screening for metric learning. Distance metric learning can optimize a metric over a set of triplets, each one of which is defined by a pair of same class instances and an instance in a different class. However, the number of possible triplets is quite huge even for a small dataset. Our safe triplet scree…

Safe RL with binary feedback using SABRE algorithm.

In high dimensional regression settings, sparsity enforcing penalties have proved useful to regularize the data-fitting term. A recently introduced technique called screening rules propose to ignore some variables in the optimization leveraging the expected sparsity of the solutions and consequently leading to faster s…

Safe imitation learning with a safety layer for flexible training.

Safe exploration framework for IML algorithms.

Safe Gaussian Process Bandit Optimization with sub-linear regret bounds.

SPIBB improves safe policy improvement with a softer baseline approach.

Safe autonomous decisions made with machine learning predictions using Conformal Decision Theory.

A new screening test for Lasso improves solution speed.

Algorithm reduces regret in safe Bayesian optimization with monotonicity constraints.

In this work we seek for an approach to integrate safety in the learning process that relies on a partly known state-space model of the system and regards the unknown dynamics as an additive bounded disturbance. We introduce a framework for safely learning a control strategy for a given system with an additive disturba…

Quantum model improves safety in machine learning.

Safe control for vehicles using learned perception from images.

Paper improves safe policy improvement with estimated baseline policy.

Adapts safe policies for exploration in high-risk settings.

RYU framework constructs safe regions for optimization problems.

Safe screening rules reduce $\ell_0$-regression computation by fixing 76% of variables.

Safe reinforcement learning framework using optimal transport for robustness.

Safe neural networks for input-output specifications.

Safe algorithm for linear bandits with safety constraints, matching previous results.

A new distributed method speeds up sparse model training.

Safe Pattern Pruning reduces pattern explosion in predictive pattern mining.

We consider the problem of learning a sparse rule model, a prediction model in the form of a sparse linear combination of rules, where a rule is an indicator function defined over a hyper-rectangle in the input space. Since the number of all possible such rules is extremely large, it has been computationally intractabl…

We present safe active incremental feature selection~(SAIF) to scale up the computation of LASSO solutions. SAIF does not require a solution from a heavier penalty parameter as in sequential screening or updating the full model for each iteration as in dynamic screening. Different from these existing screening methods,…

Safe-EF improves federated learning for non-smooth, constrained optimization.

Algorithm safely learns from sub-optimal baseline policies while satisfying constraints.

In this paper, we study the problem of safe online learning to re-rank, where user feedback is used to improve the quality of displayed lists. Learning to rank has traditionally been studied in two settings. In the offline setting, rankers are typically learned from relevance labels created by judges. This approach has…

Safe-DRFS selects features robust to covariate shifts for reliable performance.

Monotonicity helps in safely optimizing unknown functions.

A new method for safer statistical inference after predictions.

Sparse learning techniques have been routinely used for feature selection as the resulting model usually has a small number of non-zero entries. Safe screening, which eliminates the features that are guaranteed to have zero coefficients for a certain value of the regularization parameter, is a technique for improving t…

This paper addresses the question of how a previously available control policy $π_s$ can be used as a supervisor to more quickly and safely train a new learned control policy $π_L$ for a robot. A weighted average of the supervisor and learned policies is used during trials, with a heavier weight initially on the superv…

SafePILCO is a Python tool for safe reinforcement learning.

Improves policies with high certainty, even in small samples.

High dimensional regression benefits from sparsity promoting regularizations. Screening rules leverage the known sparsity of the solution by ignoring some variables in the optimization, hence speeding up solvers. When the procedure is proven not to discard features wrongly the rules are said to be \emph{safe}. In this …

Optimal and safe semi-supervised learning estimator for high-dimensional data.

Algorithm ensures safe optimization under unknown constraints.

DRSS method identifies unnecessary samples and features in DR covariate shift.

Safe screening rule reduces computational costs for Group OWL models.

A new method for CMDP solving without compromising safety constraints.