English
Related papers

Related papers: ZClassifier: Temperature Tuning and Manifold Appro…

200 papers

State-of-the-art image-set matching techniques typically implicitly model each image-set with a Gaussian distribution. Here, we propose to go beyond these representations and model image-sets as probability distribution functions (PDFs)…

Computer Vision and Pattern Recognition · Computer Science 2015-08-03 Mehrtash Harandi , Mathieu Salzmann , Mahsa Baktashmotlagh

In high dimension, low sample size (HDLSS) settings, classifiers based on Euclidean distances like the nearest neighbor classifier and the average distance classifier perform quite poorly if differences between locations of the underlying…

Methodology · Statistics 2022-03-08 Sarbojit Roy , Soham Sarkar , Subhajit Dutta , Anil K. Ghosh

The manifold hypothesis (real world data concentrates near low-dimensional manifolds) is suggested as the principle behind the effectiveness of machine learning algorithms in very high dimensional problems that are common in domains such as…

Machine Learning · Computer Science 2022-07-15 Aditya Chetan , Nipun Kwatra

Gaussian processes are notorious for scaling cubically with the size of the training set, preventing application to very large regression problems. Computation-aware Gaussian processes (CAGPs) tackle this scaling issue by exploiting…

Machine Learning · Statistics 2025-03-24 Disha Hegde , Mohamed Adil , Jon Cockayne

The problem of long-tailed recognition (LTR) has received attention in recent years due to the fundamental power-law distribution of objects in the real-world. Most recent works in LTR use softmax classifiers that are biased in that they…

Computer Vision and Pattern Recognition · Computer Science 2023-06-27 Saurabh Sharma , Yongqin Xian , Ning Yu , Ambuj Singh

Contrastive learning (CL) continuously achieves significant breakthroughs across multiple domains. However, the most common InfoNCE-based methods suffer from some dilemmas, such as \textit{uniformity-tolerance dilemma} (UTD) and…

Machine Learning · Computer Science 2023-06-13 Zizheng Huang , Haoxing Chen , Ziqi Wen , Chao Zhang , Huaxiong Li , Bo Wang , Chunlin Chen

Datasets containing both categorical and continuous variables are frequently encountered in many areas, and with the rapid development of modern measurement technologies, the dimensions of these variables can be very high. Despite the…

Methodology · Statistics 2024-01-03 Binyan Jiang , Chenlei Leng , Cheng Wang , Zhongqing Yang , Xinyang Yu

For many applications of probabilistic classifiers it is important that the predicted confidence vectors reflect true probabilities (one says that the classifier is calibrated). It has been shown that common models fail to satisfy this…

Machine Learning · Statistics 2022-10-10 Michael Panchenko , Anes Benmerzoug , Miguel de Benito Delgado

Training large language models (LLMs) presents numerous challenges, including gradient instability and loss spikes. These phenomena can lead to catastrophic divergence, requiring costly checkpoint restoration and data batch skipping.…

Machine Learning · Computer Science 2025-04-04 Abhay Kumar , Louis Owen , Nilabhra Roy Chowdhury , Fabian Güra

Sensor calibration, which can be intrinsic or extrinsic, is an essential step to achieve the measurement accuracy required for modern perception and navigation systems deployed on autonomous robots. To date, intrinsic calibration models for…

Robotics · Computer Science 2021-07-29 Jiunn-Kai Huang , Chenxi Feng , Madhav Achar , Maani Ghaffari , Jessy W. Grizzle

Despite impressive accuracy, deep neural networks are often miscalibrated and tend to overly confident predictions. Recent techniques like temperature scaling (TS) and label smoothing (LS) show effectiveness in obtaining a well-calibrated…

Computer Vision and Pattern Recognition · Computer Science 2021-09-14 Mobarakol Islam , Lalithkumar Seenivasan , Hongliang Ren , Ben Glocker

Cosine similarity is the common choice for measuring the distance between the feature representations in contrastive visual-textual alignment learning. However, empirically a learnable softmax temperature parameter is required when learning…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Zhun Sun

As a technique to bridge logit matching and probability distribution matching, temperature scaling plays a pivotal role in knowledge distillation (KD). Conventionally, temperature scaling is applied to both teacher's logits and student's…

Machine Learning · Computer Science 2024-03-11 Kaixiang Zheng , En-Hui Yang

Scaling educational assessment with large language models requires not just accuracy, but the ability to recognize when predictions are trustworthy. Instruction-tuned models tend to be overconfident, and their reliability deteriorates as…

Computation and Language · Computer Science 2026-03-13 Pranav Raikote , Korbinian Randl , Ioanna Miliou , Athanasios Lakes , Panagiotis Papapetrou

We recapitulate the Bayesian formulation of neural network based classifiers and show that, while sampling from the posterior does indeed lead to better generalisation than is obtained by standard optimisation of the cost function, even…

Machine Learning · Statistics 2019-04-09 Robert J. N. Baldock , Nicola Marzari

In many classification applications, the prediction of a deep neural network (DNN) based classifier needs to be accompanied by some confidence indication. Two popular approaches for that aim are: 1) Calibration: modifies the classifier's…

Machine Learning · Computer Science 2025-06-03 Lahav Dabah , Tom Tirer

Conventional knowledge distillation (KD) methods require access to the internal information of teachers, e.g., logits. However, such information may not always be accessible for large pre-trained language models (PLMs). In this work, we…

Computation and Language · Computer Science 2023-06-16 Qinhong Zhou , Zonghan Yang , Peng Li , Yang Liu

Score-matching generative models have proven successful at sampling from complex high-dimensional data distributions. In many applications, this distribution is believed to concentrate on a much lower $d$-dimensional manifold embedded into…

Machine Learning · Statistics 2025-04-25 Peter Potaptchik , Iskander Azangulov , George Deligiannidis

Robust classification in noisy environments remains a fundamental challenge in machine learning. Standard approaches typically treat signal enhancement and classification as separate, sequential stages: first enhancing the signal and then…

Machine Learning · Computer Science 2026-05-19 Gilad Nurko , Roi Benita , Yehoshua Dissen , Tomohiro Nakatani , Marc Delcroix , Shoko Araki , Joseph Keshet

Analyzing high-dimensional data with manifold learning algorithms often requires searching for the nearest neighbors of all observations. This presents a computational bottleneck in statistical manifold learning when observations of…

Machine Learning · Computer Science 2022-03-11 Fan Cheng , Anastasios Panagiotelis , Rob J Hyndman