Calibration and uncertainty estimation are crucial topics in high-risk environments. We introduce a new diversity regularizer for classification tasks that uses out-of-distribution samples and increases the overall accuracy, calibration and out-of-distribution detection capabilities of ensembles. Following the recent interest in the diversity of ensembles, we systematically evaluate the viability of explicitly regularizing ensemble diversity to improve calibration on in-distribution data as well as under dataset shift. We demonstrate that diversity regularization is highly beneficial in architectures, where weights are partially shared between the individual members and even allows to use fewer ensemble members to reach the same level of robustness. Experiments on CIFAR-10, CIFAR-100, and SVHN show that regularizing diversity can have a significant impact on calibration and robustness, as well as out-of-distribution detection.
Calibrating Bayesian Learning via Regularization, Confidence Minimization, and Selective Inference
King’s Communications, Learning & Information Processing (KCLIP) lab（国王通讯、学习与信息处理（KCLIP）实验室）；Centre for Intelligent Information Processing Systems (CIIPS)（智能信息处理系统中心）；Department of Engineering, King’s College London（伦敦国王学院工程系）
Deep learning is vulnerable to adversarial examples. Many defenses based on randomized neural networks have been proposed to solve the problem, but fail to achieve robustness against attacks using proxy gradients such as the Expectation over Transformation (EOT) attack. We investigate the effect of the adversarial attacks using proxy gradients on randomized neural networks and demonstrate that it highly relies on the directional distribution of the loss gradients of the randomized neural network. We show in particular that proxy gradients are less effective when the gradients are more scattere…
Deep neural networks have been shown to be highly miscalibrated. often they tend to be overconfident in their predictions. It poses a significant challenge for safety-critical systems to utilise deep neural networks (DNNs), reliably. Many recently proposed approaches to mitigate this have demonstrated substantial progress in improving DNN calibration. However, they hardly touch upon refinement, which historically has been an essential aspect of calibration. Refinement indicates separability of a network's correct and incorrect predictions. This paper presents a theoretically and empirically su…
Fine-tuned pre-trained language models can suffer from severe miscalibration for both in-distribution and out-of-distribution (OOD) data due to over-parameterization. To mitigate this issue, we propose a regularized fine-tuning method. Our method introduces two types of regularization for better calibration: (1) On-manifold regularization, which generates pseudo on-manifold samples through interpolation within the data manifold. Augmented training with these pseudo samples imposes a smoothness regularization to improve in-distribution calibration. (2) Off-manifold regularization, which encoura…
Recent works have shown that most deep learning models are often poorly calibrated, i.e., they may produce overconfident predictions that are wrong. It is therefore desirable to have models that produce predictive uncertainty estimates that are reliable. Several approaches have been proposed recently to calibrate classification models. However, there is relatively little work on calibrating regression models. We present a method for calibrating regression models based on a novel quantile regularizer defined as the cumulative KL divergence between two CDFs. Unlike most of the existing approache…
In classification applications, we often want probabilistic predictions to reflect confidence or uncertainty. Dropout, a commonly used training technique, has recently been linked to Bayesian inference, yielding an efficient way to quantify uncertainty in neural network models. However, as previously demonstrated, confidence estimates computed with a naive implementation of dropout can be poorly calibrated, particularly when using convolutional networks. In this paper, through the lens of ensemble learning, we associate calibration error with the correlation between the models sampled with dro…
From the statistical learning perspective, complexity control via explicit regularization is a necessity for improving the generalization of over-parameterized models. However, the impressive generalization performance of neural networks with only implicit regularization may be at odds with this conventional wisdom. In this work, we revisit the importance of explicit regularization for obtaining well-calibrated predictive uncertainty. Specifically, we introduce a probabilistic measure of calibration performance, which is lower bounded by the log-likelihood. We then explore explicit regularizat…
We propose a generic framework to calibrate accuracy and confidence of a prediction in deep neural networks through stochastic inferences. We interpret stochastic regularization using a Bayesian model, and analyze the relation between predictive uncertainty of networks and variance of the prediction scores obtained by stochastic inferences for a single example. Our empirical study shows that the accuracy and the score of a prediction are highly correlated with the variance of multiple stochastic inferences given by stochastic depth or dropout. Motivated by this observation, we design a novel v…
Fill In The Gaps: Model Calibration and Generalization with Synthetic Data
School of Computing and Augmented Intelligence, Arizona State University（亚利桑那州立大学计算与增强智能学院）；School of Mathematical and Natural Sciences, Arizona State University（亚利桑那州立大学数学与自然科学学院）
DOMINO++: Domain-aware Loss Regularization for Deep Learning Generalizability
University of Florida (UF)（佛罗里达大学）；Torch Technologies, LLC（Torch科技有限责任公司）；McKnight Brain Institute（麦克奈特脑研究所）；College of Public Health and Health Professions（公共卫生与健康职业学院）；College of Medicine（医学院）；United States Air Force Research Laboratory（美国空军研究实验室）；Herbert Wertheim College of Engineering（赫伯特·韦特海姆工程学院）；Department of Biomedical Engineering（生物医学工程系）；Department of Clinical and Health Psychology（临床与健康心理学系）；Department of Neuroscience（神经科学系）；Department of Electrical and Computer Engineering（电气与计算机工程系）；Department of Computer Information and Science and Engineering（计算机信息与工程系）
Arizona State University（亚利桑那州立大学）；Lawrence Livermore National Labs（劳伦斯利弗莫尔国家实验室）；IBM Research AI（IBM研究院人工智能部门）
The hypothesis that sub-network initializations (lottery) exist within the initializations of over-parameterized networks, which when trained in isolation produce highly generalizable models, has led to crucial insights into network initialization and has enabled efficient inferencing. Supervised models with uncalibrated confidences tend to be overconfident even when making wrong prediction. In this paper, for the first time, we study how explicit confidence calibration in the over-parameterized network impacts the quality of the resulting lottery tickets. More specifically, we incorporate a s…
Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial for training predictive models, even when we do not explicitly measure the uncertainties. This is conceptually similar to heteroscedastic neural networks that produce variance estimates for each prediction, with the key difference that we do not place a Gaussian prior on the predictions. We propose a novel algorithm that performs simultaneous interval estimation for different calibration levels and effectively levera…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
In this paper, sample-aware policy entropy regularization is proposed to enhance the conventional policy entropy regularization for better exploration. Exploiting the sample distribution obtainable from the replay buffer, the proposed sample-aware entropy regularization maximizes the entropy of the weighted sum of the policy action distribution and the sample action distribution from the replay buffer for sample-efficient exploration. A practical algorithm named diversity actor-critic (DAC) is developed by applying policy iteration to the objective function with the proposed sample-aware entro…
MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Rutgers University（罗格斯大学）
State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in leveraging a mix of labeled and unlabeled data by combining techniques of consistency regularization and pseudo-labeling. During pseudo-labeling, the model's predictions on unlabeled data are used for training and thus, model calibration is important in mitigating confirmation bias. Yet, many SOTA methods are optimized for model performance, with little focus directed to improve model calibration. In this work, we empirically demonstrate that model calibration is strongly correlated with model perform…
Computer Vision and Systems Laboratory / REPARTI and Big Data Research Centre（计算机视觉与系统实验室/REPARTI与大数据研究中心）；Université Laval（拉瓦尔大学）
Calibrating the confidence of supervised learning models is important for a variety of contexts where the certainty over predictions should be reliable. However, it has been reported that deep neural network models are often too poorly calibrated for achieving complex tasks requiring reliable uncertainty estimates in their prediction. In this work, we are proposing a strategy for training deep ensembles with a diversity function regularization, which improves the calibration property while maintaining a similar prediction accuracy.
Deep ensembles perform better than a single network thanks to the diversity among their members. Recent approaches regularize predictions to increase diversity; however, they also drastically decrease individual members' performances. In this paper, we argue that learning strategies for deep ensembles need to tackle the trade-off between ensemble diversity and individual accuracies. Motivated by arguments from information theory and leveraging recent advances in neural estimation of conditional mutual information, we introduce a novel training criterion called DICE: it increases diversity by r…
Recently diversity-inducing regularization methods for latent variable models (LVMs), which encourage the components in LVMs to be diverse, have been studied to address several issues involved in latent variable modeling: (1) how to capture long-tail patterns underlying data; (2) how to reduce model complexity without sacrificing expressivity; (3) how to improve the interpretability of learned patterns. While the effectiveness of diversity-inducing regularizers such as the mutual angular regularizer has been demonstrated empirically, a rigorous theoretical analysis of them is still missing. In…
Tianjin University（天津大学）；The Open University（开放大学）
Although the deep structure guarantees the powerful expressivity of deep networks (DNNs), it also triggers serious overfitting problem. To improve the generalization capacity of DNNs, many strategies were developed to improve the diversity among hidden units. However, most of these strategies are empirical and heuristic in absence of either a theoretical derivation of the diversity measure or a clear connection from the diversity to the generalization capacity. In this paper, from an information theoretic perspective, we introduce a new definition of redundancy to describe the diversity of hid…
DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning
The Ohio State University, USA（俄亥俄州立大学）；Case Western Reserve University, USA（凯斯西储大学）；The Chinese University of Hong Kong, Hong Kong（香港中文大学）；Macquarie University, Australia（麦考瑞大学）；University of Michigan, USA（密歇根大学）；The University of Hong Kong, Hong Kong（香港大学）；University College London, UK（伦敦大学学院）
Selective Learning: Towards Robust Calibration with Dynamic Regularization
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Rutgers University（罗格斯大学）；A*STAR Centre for Frontier AI Research (CFAR)（新加坡科技研究局前沿人工智能研究中心）
Kernel methods have achieved very good performance on large scale regression and classification problems, by using the Nyström method and preconditioning techniques. The Nyström approximation -- based on a subset of landmarks -- gives a low rank approximation of the kernel matrix, and is known to provide a form of implicit regularization. We further elaborate on the impact of sampling diverse landmarks for constructing the Nyström approximation in supervised as well as unsupervised kernel methods. By using Determinantal Point Processes for sampling, we obtain additional theoretical results con…
DiRe: Diversity-promoting Regularization for Dataset Condensation
Department of Artificial Intelligence, Indian Institute of Technology Hyderabad（人工智能系，印度理工学院海得拉巴）；Centre for Responsible AI, Wadhwani School of Data Science & AI, Indian Institute of Technology Madras（负责任人工智能中心，Wadhwani数据科学与人工智能学院，印度理工学院马德拉斯）
Calibrated Multivariate Distributional Regression with Pre-Rank Regularization
Department of Statistics and Data Science, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE（统计与数据科学系，Mohamed Bin Zayed人工智能大学，阿布扎比，阿联酋）
DataNova；U.S. Army Research Laboratory（美国陆军研究实验室）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
Electroencephalography (EEG) headsets are the most commonly used sensing devices for Brain-Computer Interface. In real-world applications, there are advantages to extrapolating data from one user session to another. However, these advantages are limited if the data arise from different hardware systems, which often vary between application spaces. Currently, this creates a need to recalibrate classifiers, which negatively affects people's interest in using such systems. In this paper, we employ active weighted adaptation regularization (AwAR), which integrates weighted adaptation regularizatio…
Intel Labs（英特尔实验室）；University of Central Florida（中佛罗里达大学）
The classic DQN algorithm is limited by the overestimation bias of the learned Q-function. Subsequent algorithms have proposed techniques to reduce this problem, without fully eliminating it. Recently, the Maxmin and Ensemble Q-learning algorithms have used different estimates provided by the ensembles of learners to reduce the overestimation bias. Unfortunately, these learners can converge to the same point in the parametric or representation space, falling back to the classic single neural network DQN. In this paper, we describe a regularization technique to maximize ensemble diversity in th…
National University of Singapore（新加坡国立大学）；ByteDance AI Lab（字节跳动人工智能实验室）
Deep reinforcement learning (RL) agents trained in a limited set of environments tend to suffer overfitting and fail to generalize to unseen testing environments. To improve their generalizability, data augmentation approaches (e.g. cutout and random convolution) are previously explored to increase the data diversity. However, we find these approaches only locally perturb the observations regardless of the training environments, showing limited effectiveness on enhancing the data diversity and the generalization performance. In this work, we introduce a simple approach, named mixreg, which tra…
Noise Consistency Regularization for Improved Subject-Driven Image Synthesis
The Australian National University（澳大利亚国立大学）；Rutgers University（罗格斯大学）；Data61 CSIRO（澳大利亚联邦科学与工业研究组织 Data61）；Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室）
We propose a simple yet highly effective method that addresses the mode-collapse problem in the Conditional Generative Adversarial Network (cGAN). Although conditional distributions are multi-modal (i.e., having many modes) in practice, most cGAN approaches tend to learn an overly simplified distribution where an input is always mapped to a single output regardless of variations in latent code. To address such issue, we propose to explicitly regularize the generator to produce diverse outputs depending on latent codes. The proposed regularization is simple, general, and can be easily integrate…
Several regularization methods have recently been introduced which force the latent activations of an autoencoder or deep neural network to conform to either a Gaussian or hyperspherical distribution, or to minimize the implicit rank of the distribution in latent space. In the present work, we introduce a novel regularizing loss function which simulates a pairwise repulsive force between items and an attractive force of each item toward the origin. We show that minimizing this loss function in isolation achieves a hyperspherical distribution. Moreover, when used as a regularizing term, the sca…
Reliability-Centered Evaluation of Sparse Longitudinal CT Lesion-Size Forecasting with Conformal Interval Calibration and Gompertz-Inspired Regularization
Beyond Activation Alignment:The Alignment-Diversity Tradeoff in Task-Aware LLM Quantization
South China University of Technology（华南理工大学）；Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）；Ocean University of China（中国海洋大学）；Center for AI Theoretical Foundation and Systems, Shenzhen Loop Area Institute（深圳环区研究所人工智能理论基础与系统中心）
Latent Variable Models (LVMs) are a large family of machine learning models providing a principled and effective way to extract underlying patterns, structure and knowledge from observed data. Due to the dramatic growth of volume and complexity of data, several new challenges have emerged and cannot be effectively addressed by existing LVMs: (1) How to capture long-tail patterns that carry crucial information when the popularity of patterns is distributed in a power-law fashion? (2) How to reduce model complexity and computational cost without compromising the modeling power of LVMs? (3) How t…
By using the framework of Determinantal Point Processes (DPPs), some theoretical results concerning the interplay between diversity and regularization can be obtained. In this paper we show that sampling subsets with kDPPs results in implicit regularization in the context of ridgeless Kernel Regression. Furthermore, we leverage the common setup of state-of-the-art DPP algorithms to sample multiple small subsets and use them in an ensemble of ridgeless regressions. Our first empirical results indicate that ensemble of ridgeless regressors can be interesting to use for datasets including redunda…
Delft University of Technology（代尔夫特理工大学）；Norwegian University of Science and Technology（挪威科技大学）；Radboud University（拉德堡德大学）
This paper studies user attributes in light of current concerns in the recommender system community: diversity, coverage, calibration, and data minimization. In experiments with a conventional context-aware recommender system that leverages side information, we show that user attributes do not always improve recommendation. Then, we demonstrate that user attributes can negatively impact diversity and coverage. Finally, we investigate the amount of information about users that ``survives'' from the training data into the recommendation lists produced by the recommender. This information is a we…
