Related papers: Beating the Winner's Curse via Inference-Aware Pol…

Many current applications use recommendations in order to modify the natural user behavior, such as to increase the number of sales or the time spent on a website. This results in a gap between the final recommendation objective and the…

Multi-objective learning under user-specified preference is common in real-world problems such as multi-lingual speech recognition under fairness. In this work, we frame such a problem as a semivectorial bilevel optimization problem, whose…

Reinforcement learning algorithms are typically geared towards optimizing the expected return of an agent. However, in many practical applications, low variance in the return is desired to ensure the reliability of an algorithm. In this…

We propose a novel method for inferring refinement types of higher-order functional programs. The main advantage of the proposed method is that it can infer maximally preferred (i.e., Pareto optimal) refinement types with respect to a…

Fairness and interpretability play an important role in the adoption of decision-making algorithms across many application domains. These requirements are intended to avoid undesirable group differences and to alleviate concerns related to…

Algorithmic fairness has attracted significant attention in recent years, with many quantitative measures suggested for characterizing the fairness of different machine learning algorithms. Despite this interest, the robustness of those…

Monotonic policy improvement and off-policy learning are two main desirable properties for reinforcement learning algorithms. In this paper, by lower bounding the performance difference of two policies, we show that the monotonic policy…

We work towards a unifying paradigm for accelerating policy optimization methods in reinforcement learning (RL) by integrating foresight in the policy improvement step via optimistic and adaptive updates. Leveraging the connection between…

Autonomous systems are increasingly expected to operate in the presence of adversaries, though adversaries may infer sensitive information simply by observing a system. Therefore, present a deceptive sequential decision-making framework…

We present AutoOptimization, a novel multi-objective optimization framework for adapting user interfaces. From a user's verbal preferences for changing a UI, our framework guides a prioritization-based Pareto frontier search over candidate…

Experience replay is a core ingredient of modern deep reinforcement learning, yet its benefits in policy optimization are poorly understood beyond empirical heuristics. This paper develops a novel theoretical framework for experience replay…

We study fairness-accuracy tradeoffs when a single predictive model must serve multiple demographic groups. A useful tool for understanding this tradeoff is the fairness-accuracy (FA) Pareto frontier, which characterizes the set of models…

The ability to exploit prior experience to solve novel problems rapidly is a hallmark of biological learning systems and of great practical importance for artificial ones. In the meta reinforcement learning literature much recent work has…

Algorithmic decision-making in practice must be fair for legal, ethical, and societal reasons. To achieve this, prior research has contributed various approaches that ensure fairness in machine learning predictions, while comparatively…

Agents that learn to select optimal actions represent a prominent focus of the sequential decision-making literature. In the face of a complex environment or constraints on time and resources, however, aiming to synthesize such an optimal…

We propose a novel numerical approach to compute the Pareto front in multivariate polynomial multi-objective optimization problems. When the objective functions and (equality) constraints are multivariate polynomials, the Pareto front,…

The rapid growth of data in the recent years has led to the development of complex learning algorithms that are often used to make decisions in real world. While the positive impact of the algorithms has been tremendous, there is a need to…

Many high-stake decisions follow an expert-in-loop structure in that a human operator receives recommendations from an algorithm but is the ultimate decision maker. Hence, the algorithm's recommendation may differ from the actual decision…

Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While…

There is a well known intrinsic trade-off between the fairness of a representation and the performance of classifiers derived from the representation. Due to the complexity of optimisation algorithms in most modern representation learning…