English
Related papers

Related papers: Predictable Compression Failures: Order Sensitivit…

200 papers

The indirect source-coding problem in which a Bernoulli process is compressed in a lossy manner from its noisy observations is considered. These noisy observations are obtained by passing the source sequence through a The indirect…

Information Theory · Computer Science 2015-06-05 Alon Kipnis , Stefano Rini , Andrea J. Goldsmith

A predecessor pilot (Cacioli, 2026) found that Llama-3-8B implements prompted sandbagging as positional collapse rather than answer avoidance. However, fixed option ordering in MMLU-Pro left open whether this reflected a model-level…

Computation and Language · Computer Science 2026-04-30 Jon-Paul Cacioli

Consider the problem where a statistician in a two-node system receives rate-limited information from a transmitter about marginal observations of a memoryless process generated from two possible distributions. Using its own observations,…

Information Theory · Computer Science 2017-03-02 Gil Katz , Pablo Piantanida , Mérouane Debbah

Transfer learning seeks to accelerate sequential decision-making by leveraging offline data from related agents. However, data from heterogeneous sources that differ in observed features, distributions, or unobserved confounders often…

Machine Learning · Computer Science 2025-07-10 Xueping Gong , Wei You , Jiheng Zhang

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…

Learning disentangled representations of textual data is essential for many natural language tasks such as fair classification, style transfer and sentence generation, among others. The existent dominant approaches in the context of text…

Artificial Intelligence · Computer Science 2021-05-07 Pierre Colombo , Chloe Clavel , Pablo Piantanida

Large Language Models (LLMs) exhibit impressive performance on complex reasoning tasks, yet they frequently fail on basic numerical problems, producing incorrect outputs. Inspired by Benford's Law, a statistical pattern in which lower…

Computation and Language · Computer Science 2025-12-01 Jiandong Shao , Yao Lu , Jianfei Yang

Predictive algorithms inform consequential decisions in settings with selective labels: outcomes are observed only for units selected by past decision makers. This creates an identification problem under unobserved confounding -- when…

Econometrics · Economics 2025-11-07 Ashesh Rambachan , Amanda Coston , Edward Kennedy

Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model explanations. Post-hoc model-agnostic explanation methods addresses this challenge by learning a…

Machine Learning · Computer Science 2026-03-18 Sumedha Chugh , Ranjitha Prasad , Nazreen Shah

The problem of distributed testing against independence with variable-length coding is considered when the \emph{average} and not the \emph{maximum} communication load is constrained as in previous works. The paper characterizes the optimum…

Information Theory · Computer Science 2020-05-19 Sadaf Salehkalaibar , Michele Wigger

We study the binomial channel and the structure of its capacity-achieving input and output distributions. It is known that the capacity-achieving input distribution is discrete and supported on finitely many points. The best previously…

Information Theory · Computer Science 2026-05-13 Mohammadamin Baniasadi , Luca Barletta , Alex Dytso

We derive the optimum second-order coding rates, known as second-order capacities, for erasure and list decoding. For erasure decoding for discrete memoryless channels, we show that second-order capacity is $\sqrt{V}\Phi^{-1}(\epsilon_t)$…

Information Theory · Computer Science 2014-04-22 Vincent Y. F. Tan , Pierre Moulin

In this paper, our aim is to analyse the generalization capabilities of first-order methods for statistical learning in multiple, different yet related, scenarios including supervised learning, transfer learning, robust learning and…

Machine Learning · Computer Science 2024-07-02 Kevin Scaman , Mathieu Even , Batiste Le Bars , Laurent Massoulié

Subjective evaluation of LLM behavior -- empathy, restraint, calibrated emotional tone -- is hard. Human inter-rater agreement on such qualities saturates near rho ~ 0.45, and an LLM-as-judge proxy alone risks circularity: a judge sharing…

Computation and Language · Computer Science 2026-05-28 Yuming , Huang , Yao Liu , Lei Wang , Junchen Wan

In this paper we consider the problem of binary hypothesis testing with finite memory systems. Let $X_1,X_2,\ldots$ be a sequence of independent identically distributed Bernoulli random variables, with expectation $p$ under $\mathcal{H}_0$…

Information Theory · Computer Science 2020-05-18 Tomer Berg , Ofer Shayevitz , Or Ordentlich

Large language models can follow complex procedures yet fail at a seemingly trivial final step: reporting a value they themselves computed moments earlier. We study this phenomenon as \emph{procedural hallucination}: failure to execute a…

Machine Learning · Statistics 2026-02-24 Ahmed Karim , Fatima Sheaib , Zein Khamis , Maggie Chlon , Jad Awada , Leon Chlon

Transformers achieve superior performance on many tasks, but impose heavy compute and memory requirements during inference. This inference can be made more efficient by partitioning the process across multiple devices, which, in turn,…

Machine Learning · Computer Science 2026-04-21 Anderson de Andrade , Alon Harell , Ivan V. Bajić

Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference pipeline. In a human choice blindness study, 91% of…

Computation and Language · Computer Science 2026-03-10 Wenbin Wu

Obstacles to integrability sometimes hamper the standard Normal Form analysis of perturbed integrable evolution equations. One is then forced to account for them by the Normal Form, which is the dynamical equation obeyed by the zero-order…

Exactly Solvable and Integrable Systems · Physics 2007-05-23 Alex Veksler Yair Zarmi

Adversarial training is a principled approach for training robust neural networks. Despite of tremendous successes in practice, its theoretical properties still remain largely unexplored. In this paper, we provide new theoretical insights…

Machine Learning · Computer Science 2019-07-29 Yan Li , Ethan X. Fang , Huan Xu , Tuo Zhao