A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Safe learning of stochastic dynamics with safety constraints.
Study on neural networks to identify redundancy issues in safe machine learning.
We propose a method to optimise the parameters of a policy which will be used to safely perform a given task in a data-efficient manner. We train a Gaussian process model to capture the system dynamics, based on the PILCO framework. Our model has useful analytic properties, which allow closed form computation of error …
Bayesian optimization sped up with model approximations for safe online system optimization.
Meta-active learning optimizes control of safety-critical systems by efficiently learning dynamics and configurations.
Safe RL in linear systems achieves -regret.
Safe-M-UCRL learns safe policies for multi-agent systems with global constraints.
Bandit algorithms have various application in safety-critical systems, where it is important to respect the system constraints that rely on the bandit's unknown parameters at every round. In this paper, we formulate a linear stochastic multi-armed bandit problem with safety constraints that depend (linearly) on an unkn…
Safe learning in uncertain systems with state measurements and optimization.
Safe Gaussian Process Bandit Optimization with sub-linear regret bounds.
Meta-learning priors improves safe Bayesian optimization.
World wide road traffic fatality and accident rates are high, and this is true even in technologically advanced countries like the USA. Despite the advances in Intelligent Transportation Systems, safe transportation routing i.e., finding safest routes is largely an overlooked paradigm. In recent years, large amount of …
The paper provides a non-asymptotic error bound for linear system identification under nonlinear policies.
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…
AST provides a method to validate safe autonomy without unsafe simplifications.
SAMBA improves safe reinforcement learning with active exploration metrics.
Combines Lyapunov functions with controller synthesis for safe control policies.
There have been numerous advances in reinforcement learning, but the typically unconstrained exploration of the learning process prevents the adoption of these methods in many safety critical applications. Recent work in safe reinforcement learning uses idealized models to achieve their guarantees, but these models do …
Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world systems. As a consequence, learning algorithms are rarely applied on safety-crit…
New method avoids failures in physics-constrained systems using active learning.
In Interactive Machine Learning (IML), we iteratively make decisions and obtain noisy observations of an unknown function. While IML methods, e.g., Bayesian optimization and active learning, have been successful in applications, on real-world systems they must provably avoid unsafe decisions. To this end, safe IML algo…
Paper defines ε-Safe Decision Regions for exponential family distributions and approximates them for unbalanced data.
Safe-House secures DeFi by limiting losses and enhancing security.
Fair ML systems can be safe ML systems by considering uncertainty.
Using reinforcement learning to learn control policies is a challenge when the task is complex with potentially long horizons. Ensuring adequate but safe exploration is also crucial for controlling physical systems. In this paper, we use temporal logic to facilitate specification and learning of complex tasks. We combi…
Safe Active Learning (SAL) for GPODE models improves model performance without compromising safety.
Previous work has shown the unreliability of existing algorithms in the batch Reinforcement Learning setting, and proposed the theoretically-grounded Safe Policy Improvement with Baseline Bootstrapping (SPIBB) fix: reproduce the baseline policy in the uncertain state-action pairs, in order to control the variance on th…
Safe-DRFS selects features robust to covariate shifts for reliable performance.
In reinforcement learning, agents learn by performing actions and observing their outcomes. Sometimes, it is desirable for a human operator to \textit{interrupt} an agent in order to prevent dangerous situations from happening. Yet, as part of their learning process, agents may link these interruptions, that impact the…
ARTEO algorithm optimizes safety-critical systems with uncertainty.
In classical reinforcement learning, when exploring an environment, agents accept arbitrary short term loss for long term gain. This is infeasible for safety critical applications, such as robotics, where even a single unsafe action may cause system failure. In this paper, we address the problem of safely exploring fin…
BagCert efficiently certifies robustness against adversarial patches on image classifiers.
Paper tackles safe combinatorial semi-bandits with risk constraints.
Deep neural networks have become widely used, obtaining remarkable results in domains such as computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, and bio-informatics, where they have produced results comparable to human experts. However, th…
An important problem in sequential decision-making under uncertainty is to use limited data to compute a safe policy, i.e., a policy that is guaranteed to perform at least as well as a given baseline strategy. In this paper, we develop and analyze a new model-based approach to compute a safe policy when we have access …
A model used for velocity control during car following was proposed based on deep reinforcement learning (RL). To fulfil the multi-objectives of car following, a reward function reflecting driving safety, efficiency, and comfort was constructed. With the reward function, the RL agent learns to control vehicle speed in …
Safe active learning for multi-output Gaussian processes reduces data acquisition costs and ensures safety.
Reinforcement Learning (RL) has demonstrated state-of-the-art results in a number of autonomous system applications, however many of the underlying algorithms rely on black-box predictions. This results in poor explainability of the behaviour of these systems, raising concerns as to their use in safety-critical applica…
We introduce the safe linear stochastic bandit framework---a generalization of linear stochastic bandits---where, in each stage, the learner is required to select an arm with an expected reward that is no less than a predetermined (safe) threshold with high probability. We assume that the learner initially has knowledg…
Motivated by vision-based control of autonomous vehicles, we consider the problem of controlling a known linear dynamical system for which partial state information, such as vehicle position, is extracted from complex and nonlinear data, such as a camera image. Our approach is to use a learned perception map that predi…
New risk metric for AI systems reduces safety risks with minimal data.
Safe offline RL for chemical reactors using input convex neural networks.
The paper tackles safe reinforcement learning with convex regularization.
CoCoRL learns safe constraints from demonstrations with unknown rewards.
Many online platforms have deployed anti-fraud systems to detect and prevent fraudulent activities. However, there is usually a gap between the time that a user commits a fraudulent action and the time that the user is suspended by the platform. How to detect fraudsters in time is a challenging problem. Most of the exi…
SAFE automates feature engineering for industrial tasks efficiently and scalably.
SafePILCO is a Python tool for safe reinforcement learning.
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 …