English
Related papers

Related papers: Learning from Informants: Relations between Learni…

200 papers

We define {\em predictive information} $I_{\rm pred} (T)$ as the mutual information between the past and the future of a time series. Three qualitatively different behaviors are found in the limit of large observation times $T$: $I_{\rm…

Data Analysis, Statistics and Probability · Physics 2011-11-10 William Bialek , Ilya Nemenman , Naftali Tishby

We provide a wide-ranging study of the scenario where a subset of the relations in a relational vocabulary are visible to a user --- that is, their complete contents are known --- while the remaining relations are invisible. We also have a…

Logic in Computer Science · Computer Science 2018-05-15 Michael Benedikt , Pierre Bourhis , Balder ten Cate , Gabriele Puppis , Michael Vanden Boom

Learning from indirect supervision signals is important in real-world AI applications when, often, gold labels are missing or too costly. In this paper, we develop a unified theoretical framework for multi-class classification when the…

Machine Learning · Computer Science 2020-11-12 Kaifu Wang , Qiang Ning , Dan Roth

We investigate a population of binary mistake sequences that result from learning with parametric models of different order. We obtain estimates of their error, algorithmic complexity and divergence from a purely random Bernoulli sequence.…

Artificial Intelligence · Computer Science 2010-10-14 Joel Ratsaby

Appropriate credit assignment for delay rewards is a fundamental challenge for reinforcement learning. To tackle this problem, we introduce a delay reward calibration paradigm inspired from a classification perspective. We hypothesize that…

Machine Learning · Computer Science 2021-08-26 Yixuan Liu , Hu Wang , Xiaowei Wang , Xiaoyue Sun , Liuyue Jiang , Minhui Xue

In this position paper, I first describe a new perspective on machine learning (ML) by four basic problems (or levels), namely, "What to learn?", "How to learn?", "What to evaluate?", and "What to adjust?". The paper stresses more on the…

Information Theory · Computer Science 2015-01-20 Bao-Gang Hu

Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems. Despite this, there…

Machine Learning · Computer Science 2020-10-14 Heinrich Jiang , Qijia Jiang , Aldo Pacchiano

In language learning in the limit we investigate computable devices (learners) learning formal languages. Through the years, many natural restrictions have been imposed on the studied learners. As such, monotonic restrictions always enjoyed…

Machine Learning · Computer Science 2020-10-20 Vanja Doskoč , Timo Kötzing

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes…

Machine Learning · Computer Science 2019-06-25 Rohin Shah , Noah Gundotra , Pieter Abbeel , Anca D. Dragan

The goal of this article is to investigate how human participants allocate their limited time to decisions with different properties. We report the results of two behavioral experiments. In each trial of the experiments, the participant…

Neurons and Cognition · Quantitative Biology 2016-07-20 Arash Khodadadi , Pegah Fakhari , Jerome R. Busemeyer

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

This paper considers a variant of the classical online learning problem with expert predictions. Our model's differences and challenges are due to lacking any direct feedback on the loss each expert incurs at each time step $t$. We propose…

Machine Learning · Computer Science 2020-01-07 Yang Liu , David P. Helmbold

Standard imitation learning can fail when the expert demonstrators have different sensory inputs than the imitating agent. This is because partial observability gives rise to hidden confounders in the causal graph. In previous work, to work…

Machine Learning · Computer Science 2024-08-27 Risto Vuorio , Pim de Haan , Johann Brehmer , Hanno Ackermann , Daniel Dijkman , Taco Cohen

Alignment via reinforcement learning from human feedback (RLHF) has become the dominant paradigm for controlling the quality of outputs from large language models (LLMs). However, existing theories do not provide strong justification for…

Machine Learning · Computer Science 2026-05-19 Jihun Yun , Juno Kim , Jongho Park , Junhyuck Kim , Jongha Jon Ryu , Jaewoong Cho , Kwang-Sung Jun

Information theory provides tools to predict the performance of a learning algorithm on a given dataset. For instance, the accuracy of learning an unknown parameter can be upper bounded by reducing the learning task to hypothesis testing…

Quantum Physics · Physics 2026-04-21 Evan Peters

Automated feedback generation has the potential to enhance students' learning progress by providing timely and targeted feedback. Moreover, it can assist teachers in optimizing their time, allowing them to focus on more strategic and…

Computation and Language · Computer Science 2025-08-18 Sylvio Rüdian , Yassin Elsir , Marvin Kretschmer , Sabine Cayrou , Niels Pinkwart

How can pretrained language models (PLMs) learn factual knowledge from the training set? We investigate the two most important mechanisms: reasoning and memorization. Prior work has attempted to quantify the number of facts PLMs learn, but…

Computation and Language · Computer Science 2020-10-13 Nora Kassner , Benno Krojer , Hinrich Schütze

The exploration of whether agents can align with their environment without relying on human-labeled data presents an intriguing research topic. Drawing inspiration from the alignment process observed in intelligent organisms, where…

Computation and Language · Computer Science 2024-03-06 Bo Wang , Tianxiang Sun , Hang Yan , Siyin Wang , Qingyuan Cheng , Xipeng Qiu

People learn about opportunities and actions by observing the experiences of their friends. We model how homophily -- the tendency to associate with similar others -- affects both the endogenous quality and diversity of the information…

Theoretical Economics · Economics 2026-02-03 Yunus C. Aybas , Matthew O. Jackson

Complex classifiers may exhibit "embarassing" failures in cases where humans can easily provide a justified classification. Avoiding such failures is obviously of key importance. In this work, we focus on one such setting, where a label is…

Machine Learning · Computer Science 2019-06-14 Deborah Cohen , Amit Daniely , Amir Globerson , Gal Elidan