English
Related papers

Related papers: Loss Estimators Improve Model Generalization

200 papers

We present a new perspective on loss minimization and the recent notion of Omniprediction through the lens of Outcome Indistingusihability. For a collection of losses and hypothesis class, omniprediction requires that a predictor provide a…

Machine Learning · Computer Science 2022-12-09 Parikshit Gopalan , Lunjia Hu , Michael P. Kim , Omer Reingold , Udi Wieder

We consider the problem of uncertainty estimation in the context of (non-Bayesian) deep neural classification. In this context, all known methods are based on extracting uncertainty signals from a trained network optimized to solve the…

Machine Learning · Computer Science 2019-04-25 Yonatan Geifman , Guy Uziel , Ran El-Yaniv

Two commonly used methods for improving precision and power in clinical trials are stratified randomization and covariate adjustment. However, many trials do not fully capitalize on the combined precision gains from these two methods, which…

As large language models (LLMs) continue to evolve, understanding and quantifying the uncertainty in their predictions is critical for enhancing application credibility. However, the existing literature relevant to LLM uncertainty…

Computation and Language · Computer Science 2024-10-22 Hsiu-Yuan Huang , Yutong Yang , Zhaoxi Zhang , Sanwoo Lee , Yunfang Wu

Approximate learning machines have become popular in the era of small devices, including quantised, factorised, hashed, or otherwise compressed predictors, and the quest to explain and guarantee good generalisation abilities for such…

Machine Learning · Computer Science 2022-03-16 Andrew J. Turner , Ata Kabán

In modern deep learning, the models are learned by applying gradient updates using an optimizer, which transforms the updates based on various statistics. Optimizers are often hand-designed and tuning their hyperparameters is a big part of…

Machine Learning · Computer Science 2024-10-08 Gus Kristiansen , Mark Sandler , Andrey Zhmoginov , Nolan Miller , Anirudh Goyal , Jihwan Lee , Max Vladymyrov

Discriminator Guidance has become a popular method for efficiently refining pre-trained Score-Matching Diffusion models. However, in this paper, we demonstrate that the standard implementation of this technique does not necessarily lead to…

Machine Learning · Computer Science 2025-06-12 Alexandre Verine , Ahmed Mehdi Inane , Florian Le Bronnec , Benjamin Negrevergne , Yann Chevaleyre

Uncertainty estimation is an essential step in the evaluation of the robustness for deep learning models in computer vision, especially when applied in risk-sensitive areas. However, most state-of-the-art deep learning models either fail to…

Computer Vision and Pattern Recognition · Computer Science 2022-01-12 Lu Mi , Hao Wang , Yonglong Tian , Hao He , Nir Shavit

The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training. Domain adaptation techniques alleviate this, but need some instances from the target domain to…

Machine Learning · Computer Science 2019-06-11 Yiying Li , Yongxin Yang , Wei Zhou , Timothy M. Hospedales

In this paper, we present results on improving out-of-domain weather prediction and uncertainty estimation as part of the \texttt{Shifts Challenge on Robustness and Uncertainty under Real-World Distributional Shift} challenge. We find that…

Machine Learning · Computer Science 2024-01-10 Sankalp Gilda , Neel Bhandari , Wendy Mak , Andrea Panizza

Though black-box predictors are state-of-the-art for many complex tasks, they often fail to properly quantify predictive uncertainty and may provide inappropriate predictions for unfamiliar data. Instead, we can learn more reliable models…

Machine Learning · Statistics 2021-12-14 Jean Feng , Arjun Sondhi , Jessica Perry , Noah Simon

Distribution shifts are problems where the distribution of data changes between training and testing, which can significantly degrade the performance of a model deployed in the real world. Recent studies suggest that one reason for the…

Machine Learning · Computer Science 2023-04-10 Takuro Kutsuna

Deep learning models perform best when tested on target (test) data domains whose distribution is similar to the set of source (train) domains. However, model generalization can be hindered when there is significant difference in the…

Computer Vision and Pattern Recognition · Computer Science 2020-08-19 Pulkit Khandelwal , Paul Yushkevich

In prediction problems, it is common to model the data-generating process and then use a model-based procedure, such as a Bayesian predictive distribution, to quantify uncertainty about the next observation. However, if the posited model is…

Methodology · Statistics 2021-07-06 Pei-Shien Wu , Ryan Martin

Understanding how different classes are distributed in an unlabeled data set is an important challenge for the calibration of probabilistic classifiers and uncertainty quantification. Approaches like adjusted classify and count, black-box…

Machine Learning · Statistics 2024-06-19 Albert Ziegler , Paweł Czyż

Covariate-adaptive randomization is widely used in clinical trials to balance prognostic factors, and regression adjustments are often adopted to further enhance the estimation and inference efficiency. In practice, the covariates may…

Methodology · Statistics 2025-08-15 Wanjia Fu , Yingying Ma , Hanzhong Liu

Statistical models incorporating change points are common in practice, especially in the area of biomedicine. This approach is appealing in that a specific parameter is introduced to account for the abrupt change in the response variable…

Statistics Theory · Mathematics 2008-12-18 Hongling Zhou , Kung-Yee Liang

Decoding strategies manipulate the probability distribution underlying the output of a language model and can therefore affect both generation quality and its uncertainty. In this study, we investigate the impact of decoding strategies on…

Computation and Language · Computer Science 2025-09-23 Wataru Hashimoto , Hidetaka Kamigaito , Taro Watanabe

Complementary features of randomized controlled trials (RCTs) and observational studies (OSs) can be used jointly to estimate the average treatment effect of a target population. We propose a calibration weighting estimator that enforces…

Methodology · Statistics 2022-02-16 Dasom Lee , Shu Yang , Lin Dong , Xiaofei Wang , Donglin Zeng , Jianwen Cai

We propose a new method for estimating causal effects in longitudinal/panel data settings that we call generalized difference-in-differences. Our approach unifies two alternative approaches in these settings: ignorability estimators (e.g.,…

Methodology · Statistics 2023-12-12 Denis Agniel , Max Rubinstein , Jessie Coe , Maria DeYoreo