English
Related papers

Related papers: Probing Routing-Conditional Calibration in Attenti…

200 papers

Can a transformer learn which attention entries matter during training? In principle, yes: attention distributions are highly concentrated, and a small gate network can identify the important entries post-hoc with near-perfect accuracy. In…

Machine Learning · Computer Science 2026-03-04 Keston Aquino-Michaels

Cooperative Adaptive Cruise Control (CACC) enables vehicle platooning through inter-vehicle communication, improving traffic efficiency and safety. Conventional CACC relies on feedback linearization, assuming exact vehicle parameters;…

Systems and Control · Electrical Eng. & Systems 2026-02-12 Mischa Huisman , Thomas Arnold , Erjen Lefeber , Nathan van de Wouw , Carlos Murguia

Randomized controlled trials often do not represent the populations where decisions are made, and covariate shift across studies can invalidate standard IPD meta-analysis and transport estimators. We propose a placebo-anchored transport…

Machine Learning · Statistics 2026-04-08 Zilong Wang , Ali Abdeen , Turgay Ayer

As machine learning techniques become widely adopted in new domains, especially in safety-critical systems such as autonomous vehicles, it is crucial to provide accurate output uncertainty estimation. As a result, many approaches have been…

Machine Learning · Computer Science 2021-12-28 Sooyong Jang , Radoslav Ivanov , Insup Lee , James Weimer

Modern software-defined networks, such as Open Radio Access Network (O-RAN) systems, rely on artificial intelligence (AI)-powered applications running on controllers interfaced with the radio access network. To ensure that these AI…

Signal Processing · Electrical Eng. & Systems 2025-02-06 Seonghoon Yoo , Sangwoo Park , Petar Popovski , Joonhyuk Kang , Osvaldo Simeone

We prove a fundamental impossibility theorem: neural networks cannot simultaneously learn well-calibrated confidence estimates with meaningful diversity when trained using binary correct/incorrect supervision. Through rigorous mathematical…

Machine Learning · Computer Science 2025-09-19 Arjun S. Nair , Kristina P. Sinaga

While modern deep neural networks are performant perception modules, performance (accuracy) alone is insufficient, particularly for safety-critical robotic applications such as self-driving vehicles. Robot autonomy stacks also require these…

Computer Vision and Pattern Recognition · Computer Science 2021-09-29 Dhaivat Bhatt , Kaustubh Mani , Dishank Bansal , Krishna Murthy , Hanju Lee , Liam Paull

Conditional depth execution routes a subset of tokens through a lightweight cheap FFN while the remainder execute the standard full FFN at each controlled layer. The central difficulty is gate training: the gate decision must propagate…

Machine Learning · Computer Science 2026-04-21 Qingwei Lin

AI agents are rapidly advancing from passive language models to autonomous systems executing complex, multi-step tasks. Yet their overconfidence in failure remains a fundamental barrier to deployment in high-stakes settings. Existing…

Artificial Intelligence · Computer Science 2026-01-23 Jiaxin Zhang , Caiming Xiong , Chien-Sheng Wu

In this paper, we study the post-hoc calibration of modern neural networks, a problem that has drawn a lot of attention in recent years. Many calibration methods of varying complexity have been proposed for the task, but there is no…

Machine Learning · Computer Science 2022-08-02 Sergio A. Balanya , Juan Maroñas , Daniel Ramos

Randomized controlled trials (RCTs) are the gold standard for estimating heterogeneous treatment effects, yet they are often underpowered for detecting effect heterogeneity. Large observational studies (OS) can supplement RCTs for…

Machine Learning · Computer Science 2026-04-07 Amir Asiaee , Samhita Pal

In today's AI-assisted software engineering landscape, developers increasingly depend on LLMs that are highly capable, yet inherently imperfect. The tendency of these models to produce incorrect outputs can reduce developer productivity. To…

Software Engineering · Computer Science 2026-04-09 Hong Yi Lin , Chunhua Liu , Haoyu Gao , Patanamon Thongtanunam , Christoph Treude

The validity of statistical inference depends critically on how data are collected. When data gathered through active data collection (ADC) are reused for a post-hoc inferential task, conventional inference can fail because the sampling is…

Machine Learning · Statistics 2026-05-13 Shuichi Nishino , Tomohiro Shiraishi , Teruyuki Katsuoka , Ichiro Takeuchi

Post-training improves large language models (LLMs) but often worsens confidence calibration, leading to systematic overconfidence. Recent unsupervised post-hoc methods for post-trained LMs (PoLMs) mitigate this by aligning PoLM confidence…

Machine Learning · Computer Science 2026-01-09 Beier Luo , Cheng Wang , Hongxin Wei , Sharon Li , Xuefeng Du

A reliable deep learning system should be able to accurately express its confidence with respect to its predictions, a quality known as calibration. One of the most effective ways to produce reliable confidence estimates with a pre-trained…

Machine Learning · Computer Science 2024-10-10 Thomas P. Zollo , Zhun Deng , Jake C. Snell , Toniann Pitassi , Richard Zemel

This paper analyzes the performance of clustered decode-and-forward multi-hop relaying (CDFMR) wireless Rayleigh fading networks, and sheds light on their design principles for energy and spectral efficiency. The focus is on a general…

Information Theory · Computer Science 2014-07-01 Amin Azari , Jalil Seifali Harsini , Farshad Lahouti

Multicalibration requires predicted scores to agree with label probabilities across rich families of subgroups and score-dependent tests, but existing methods require clean input-label pairs for evaluation and post-processing. This…

Machine Learning · Statistics 2026-05-12 Futoshi Futami , Takashi Ishida

We conduct an extensive study on the state of calibration under real-world dataset shift for image classification. Our work provides important insights on the choice of post-hoc and in-training calibration techniques, and yields practical…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Mélanie Roschewitz , Raghav Mehta , Fabio de Sousa Ribeiro , Ben Glocker

In observational causal inference, domain knowledge often leaves multiple covariate adjustments plausible, yet which sets satisfy ignorability is untestable. Different adjustment sets can yield conflicting estimates of the average treatment…

Methodology · Statistics 2026-03-23 Aditya Ghosh , Dominik Rothenhäusler

We identify a previously unknown calibration property of large language models: providing one confirmed intermediate fact toward a multi-step reasoning chain increases the model's confident-wrong-answer rate before full evidence eliminates…

Computation and Language · Computer Science 2026-04-30 Ashish Balkishan Lathkar