Related papers: IReEn: Reverse-Engineering of Black-Box Functions …

Recently, interpretable machine learning has re-explored concept bottleneck models (CBM). An advantage of this model class is the user's ability to intervene on predicted concept values, affecting the downstream output. In this work, we…

Simulation plays a key role in scaling robot learning and validating policies, but constructing simulations remains a labor-intensive process. This paper introduces ReGen, a generative simulation framework that automates simulation design…

Spreadsheet workbook contents are simple programs. Because of this, probabilistic programming techniques can be used to perform Bayesian inversion of spreadsheet computations. What is more, existing execution engines in spreadsheet…

Self-trained autonomous agents developed using machine learning are showing great promise in a variety of control settings, perhaps most remarkably in applications involving autonomous vehicles. The main challenge associated with…

Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data, leading to impressive performance across a range of downstream applications. Current methods often rely on human-annotated…

The use of deep learning techniques has achieved significant progress for program synthesis from input-output examples. However, when the program semantics become more complex, it still remains a challenge to synthesize programs that are…

Deep learning techniques are rapidly advanced recently, and becoming a necessity component for widespread systems. However, the inference process of deep learning is black-box, and not very suitable to safety-critical systems which must…

We provide tools for sharing sensitive data when the data curator does not know in advance what questions an (untrusted) analyst might ask about the data. The analyst can specify a program that they want the curator to run on the dataset.…

Artificial intelligence, particularly through recent advancements in deep learning, has achieved exceptional performances in many tasks in fields such as natural language processing and computer vision. In addition to desirable evaluation…

An important aspect of developing reliable deep learning systems is devising strategies that make these systems robust to adversarial attacks. There is a long line of work that focuses on developing defenses against these attacks, but…

When the inverse of an algorithm is well-defined -- that is, when its output can be deterministically transformed into the input producing it -- we say that the algorithm is invertible. While one can describe an invertible algorithm using a…

Motivated by algorithmic information theory, the problem of program discovery can help find candidates of underlying generative mechanisms of natural and artificial phenomena. The uncomputability of such inverse problem, however,…

Designers of AI agents often iterate on the reward function in a trial-and-error process until they get the desired behavior, but this only guarantees good behavior in the training environment. We propose structuring this process as a…

We analyze the language learned by an agent trained with reinforcement learning as a component of the ActiveQA system [Buck et al., 2017]. In ActiveQA, question answering is framed as a reinforcement learning task in which an agent sits…

Circuit compilation, a crucial process for adapting quantum algorithms to hardware constraints, often operates as a ``black box,'' with limited visibility into the optimization techniques used by proprietary systems or advanced open-source…

This paper considers the problem of evaluating an autonomous system's competency in performing a task, particularly when working in dynamic and uncertain environments. The inherent opacity of machine learning models, from the perspective of…

The rule extraction literature contains the notion of a fidelity-accuracy dilemma: when building an interpretable model of a black box function, optimising for fidelity is likely to reduce performance on the underlying task, and vice versa.…

Generalizing earlier work characterizing the quantum query complexity of computing a function of an unknown classical ``black box'' function drawn from some set of such black box functions, we investigate a more general quantum query model…

This paper develops a new approach for estimating an interpretable, relational model of a black-box autonomous agent that can plan and act. Our main contributions are a new paradigm for estimating such models using a minimal query interface…

Automatic programming, the task of generating computer programs compliant with a specification without a human developer, is usually tackled either via genetic programming methods based on mutation and recombination of programs, or via…