English
Related papers

Related papers: On the Expressiveness of Assignment Messages

200 papers

Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. However, many neurons exhibit $\textit{mixed selectivity}$, i.e., they represent multiple unrelated features. A…

Machine Learning · Statistics 2023-10-19 David Klindt , Sophia Sanborn , Francisco Acosta , Frédéric Poitevin , Nina Miolane

We investigate the representation and complete representation classes for algebras of partial functions with the signature of relative complement and domain restriction. We provide and prove the correctness of a finite equational…

Logic · Mathematics 2022-12-05 Célia Borlido , Brett McLean

For representation by partial functions in the signature with intersection, composition and antidomain, we show that a representation is meet complete if and only if it is join complete. We show that a representation is complete if and only…

Rings and Algebras · Mathematics 2017-08-01 Brett McLean

Human communication is often implicit, conveying tone, identity, and intent beyond literal meanings. While large language models have achieved strong performance on explicit tasks such as summarization and reasoning, their capacity for…

Computation and Language · Computer Science 2026-02-09 Joshua Tint , Som Sagar , Aditya Taparia , Kelly Raines , Bimsara Pathiraja , Caleb Liu , Ransalu Senanayake

Extension problems for polynomial valuations on different cones of convex functions are investigated. It is shown that for the classes of functions under consideration, the extension problem reduces to a simple geometric obstruction on the…

Functional Analysis · Mathematics 2024-08-14 Jonas Knoerr , Jacopo Ulivelli

This preliminary report addresses the expressive power of unit resolution regarding input data encoded with partial truth assignments of propositional variables. A characterization of the functions that are computable in this way, which we…

Artificial Intelligence · Computer Science 2011-06-20 Olivier Bailleux

Feature attributions attempt to highlight what inputs drive predictive power. Good attributions or explanations are thus those that produce inputs that retain this predictive power; accordingly, evaluations of explanations score their…

Machine Learning · Computer Science 2024-12-20 Aahlad Puli , Nhi Nguyen , Rajesh Ranganath

Representation learning is a central challenge across a range of machine learning areas. In reinforcement learning, effective and functional representations have the potential to tremendously accelerate learning progress and solve more…

Machine Learning · Computer Science 2019-01-30 Dibya Ghosh , Abhishek Gupta , Sergey Levine

Reinforcement learning algorithms can solve dynamic decision-making and optimal control problems. With continuous-valued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value…

Machine Learning · Computer Science 2021-11-16 Jiří Kubalík , Erik Derner , Jan Žegklitz , Robert Babuška

All continuous, SL$(n)$ and translation invariant valuations on the space of convex functions on ${\mathbb R}^n$ are completely classified.

Functional Analysis · Mathematics 2019-06-18 Andrea Colesanti , Monika Ludwig , Fabian Mussnig

Explainability has become a valuable tool in the last few years, helping humans better understand AI-guided decisions. However, the classic explainability tools are sometimes quite limited when considering high-dimensional inputs and neural…

Machine Learning · Computer Science 2023-11-23 Odelia Melamed , Rich Caruana

We classify irreducible representations of the special linear groups in positive characteristic with small weight multiplicities with respect to the group rank and give estimates for the maximal weight multiplicities. For the natural…

Representation Theory · Mathematics 2013-10-01 Alexander Baranov , Anna Osinovskaya , Irina Suprunenko

We consider the problem of efficient credit assignment in reinforcement learning. In order to efficiently and meaningfully utilize new data, we propose to explicitly assign credit to past decisions based on the likelihood of them having led…

Recent efforts to learn reward functions from human feedback have tended to use deep neural networks, whose lack of transparency hampers our ability to explain agent behaviour or verify alignment. We explore the merits of learning…

Machine Learning · Computer Science 2022-10-04 Tom Bewley , Jonathan Lawry , Arthur Richards , Rachel Craddock , Ian Henderson

Although deep reinforcement learning has advanced significantly over the past several years, sample efficiency remains a major challenge. Careful choice of input representations can help improve efficiency depending on the structure present…

Machine Learning · Computer Science 2019-05-08 John Mern , Dorsa Sadigh , Mykel Kochenderfer

The low-level sensory and motor signals in deep reinforcement learning, which exist in high-dimensional spaces such as image observations or motor torques, are inherently challenging to understand or utilize directly for downstream tasks.…

Artificial Intelligence · Computer Science 2023-03-07 Pu Hua , Yubei Chen , Huazhe Xu

Given a machine learning (ML) model and a prediction, explanations can be defined as sets of features which are sufficient for the prediction. In some applications, and besides asking for an explanation, it is also critical to understand…

Machine Learning · Computer Science 2023-02-08 Xuanxiang Huang , Martin C. Cooper , Antonio Morgado , Jordi Planes , Joao Marques-Silva

We show that arithmetic definability of henselian valuations is preserved by the tilting correspondence. Moreover, we show that if a perfectoid valuation is arithmetically definable, then no parameters are needed. We also investigate…

Interpretability of learning-to-rank models is a crucial yet relatively under-examined research area. Recent progress on interpretable ranking models largely focuses on generating post-hoc explanations for existing black-box ranking models,…

We take a formal approach to the explainability problem of machine learning systems. We argue against the practice of interpreting black-box models via attributing scores to input components due to inherently conflicting goals of…

Machine Learning · Computer Science 2023-06-13 Kai Jia , Pasapol Saowakon , Limor Appelbaum , Martin Rinard