English
Related papers

Related papers: A Controlled Counterexample to Strong Proxy-Based …

200 papers

It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence. In this work, we take the opposite stance: an overly confident model is more likely to be vulnerable to…

Machine Learning · Computer Science 2018-02-14 Angus Galloway , Graham W. Taylor , Medhat Moussa

Every prediction is ultimately used in a downstream task. Consequently, evaluating prediction quality is more meaningful when considered in the context of its downstream use. Metrics based solely on predictive performance often diverge from…

Machine Learning · Computer Science 2025-08-26 Novin Shahroudi , Viacheslav Komisarenko , Meelis Kull

In recent years, graph prompting has emerged as a promising research direction, enabling the learning of additional tokens or subgraphs appended to the original graphs without requiring retraining of pre-trained graph models across various…

Machine Learning · Computer Science 2025-05-28 Qunzhong Wang , Xiangguo Sun , Hong Cheng

While metrics available during pre-training, such as perplexity, correlate well with model performance at scaling-laws studies, their predictive capacities at a fixed model size remain unclear, hindering effective model selection and…

Computation and Language · Computer Science 2025-10-17 Hansi Zeng , Kai Hui , Honglei Zhuang , Zhen Qin , Zhenrui Yue , Hamed Zamani , Dana Alon

We consider causal inference in the presence of unobserved confounding. We study the case where a proxy is available for the unobserved confounding in the form of a network connecting the units. For example, the link structure of a social…

Machine Learning · Statistics 2019-06-03 Victor Veitch , Yixin Wang , David M. Blei

Unsupervised pretraining and dropout have been well studied, especially with respect to regularization and output consistency. However, our understanding about the explicit convergence rates of the parameter estimates, and their dependence…

Machine Learning · Computer Science 2017-02-23 Vamsi K. Ithapu , Sathya Ravi , Vikas Singh

Large pretrained language models have been performing increasingly well in a variety of downstream tasks via prompting. However, it remains unclear from where the model learns the task-specific knowledge, especially in a zero-shot setup. In…

Computation and Language · Computer Science 2022-05-26 Xiaochuang Han , Yulia Tsvetkov

We study learning to learn for the multi-task structured bandit problem where the goal is to learn a near-optimal algorithm that minimizes cumulative regret. The tasks share a common structure and an algorithm should exploit the shared…

Machine Learning · Computer Science 2025-10-24 Subhojyoti Mukherjee , Josiah P. Hanna , Qiaomin Xie , Robert Nowak

We initiate an investigation of learning tasks in a setting where the learner is given access to two competing provers, only one of which is honest. Specifically, we consider the power of such learners in assessing purported properties of…

Machine Learning · Statistics 2026-03-13 Ran Canetti , Ephraim Linder , Connor Wagaman

A number of studies have proposed to use domain adaptation to reduce the training efforts needed to control an upper-limb prosthesis exploiting pre-trained models from prior subjects. These studies generally reported impressive reductions…

Machine Learning · Computer Science 2017-02-28 Valentina Gregori , Arjan Gijsberts , Barbara Caputo

Large, pre-trained models are problematic to use in resource constrained applications. Fortunately, task-aware structured pruning methods offer a solution. These approaches reduce model size by dropping structural units like layers and…

Computation and Language · Computer Science 2023-11-14 Lucio Dery , David Grangier , Awni Hannun

High complexity models are notorious in machine learning for overfitting, a phenomenon in which models well represent data but fail to generalize an underlying data generating process. A typical procedure for circumventing overfitting…

Machine Learning · Statistics 2025-03-11 James Schmidt

It is often remarked that neural networks fail to increase their uncertainty when predicting on data far from the training distribution. Yet naively using softmax confidence as a proxy for uncertainty achieves modest success in tasks…

Machine Learning · Computer Science 2021-06-10 Tim Pearce , Alexandra Brintrup , Jun Zhu

Models need appropriate inductive biases to effectively learn from small amounts of data and generalize systematically outside of the training distribution. While Transformers are highly versatile and powerful, they can still benefit from…

Computation and Language · Computer Science 2024-07-08 Matthias Lindemann , Alexander Koller , Ivan Titov

Pretraining produces a learned parameter vector that is typically treated as a starting point for further iterative adaptation. In this work, we instead view the outcome of pretraining as a distribution over parameter vectors, whose support…

Machine Learning · Computer Science 2026-03-13 Yulu Gan , Phillip Isola

Linear probes are a promising approach for monitoring AI systems for deceptive behaviour. Previous work has shown that a linear classifier trained on a contrastive instruction pair and a simple dataset can achieve good performance. However,…

Artificial Intelligence · Computer Science 2026-02-03 Vikram Natarajan , Devina Jain , Shivam Arora , Satvik Golechha , Joseph Bloom

Statistical prediction models are often trained on data from different probability distributions than their eventual use cases. One approach to proactively prepare for these shifts harnesses the intuition that causal mechanisms should…

Machine Learning · Computer Science 2023-08-02 Bijan Mazaheri , Atalanti Mastakouri , Dominik Janzing , Michaela Hardt

Large pretrained foundation models demonstrate exceptional performance and, in some high-stakes applications, even surpass human experts. However, most of these models are currently evaluated primarily on prediction accuracy, overlooking…

Machine Learning · Computer Science 2024-11-08 Tang Li , Mengmeng Ma , Xi Peng

We provide novel theoretical insights on structured prediction in the context of efficient convex surrogate loss minimization with consistency guarantees. For any task loss, we construct a convex surrogate that can be optimized via…

Machine Learning · Computer Science 2018-01-30 Anton Osokin , Francis Bach , Simon Lacoste-Julien

The fast growth of renewable energies increases the power congestion risk. To address this issue, the French Transmission System Operator (RTE) has developed closed-loop controllers to handle congestion. RTE wishes to estimate the…

Applications · Statistics 2024-04-12 Pierre Houdouin , Manuel Ruiz , Patrick Panciatici