The choice of the control frequency of a system has a relevant impact on the ability of reinforcement learning algorithms to learn a highly performing policy. In this paper, we introduce the notion of action persistence that consists in the repetition of an action for a fixed number of decision steps, having the effect of modifying the control frequency. We start analyzing how action persistence affects the performance of the optimal policy, and then we present a novel algorithm, Persistent Fitted Q-Iteration (PFQI), that extends FQI, with the goal of learning the optimal value function at a given persistence. After having provided a theoretical study of PFQI and a heuristic approach to identify the optimal persistence, we present an experimental campaign on benchmark domains to show the advantages of action persistence and proving the effectiveness of our persistence selection method.
The Ohio State University（俄亥俄州立大学）；University of Utah（犹他大学）；Southern University of Science and Technology（南方科技大学）
Variance-reduced algorithms, although achieve great theoretical performance, can run slowly in practice due to the periodic gradient estimation with a large batch of data. Batch-size adaptation thus arises as a promising approach to accelerate such algorithms. However, existing schemes either apply prescribed batch-size adaption rule or exploit the information along optimization path via additional backtracking and condition verification steps. In this paper, we propose a novel scheme, which eliminates backtracking line search but still exploits the information along optimization path by adapt…
INRIA Lille（法国国家信息与自动化研究所里尔中心）；Politecnico di Milano（米兰理工大学）
In this paper, we propose a novel approach to automatically determine the batch size in stochastic gradient descent methods. The choice of the batch size induces a trade-off between the accuracy of the gradient estimate and the cost in terms of samples of each update. We propose to determine the batch size by optimizing the ratio between a lower bound to a linear or quadratic Taylor approximation of the expected improvement and the number of samples used to estimate the gradient. The performance of the proposed approach is empirically compared with related methods on popular classification tas…
We propose a novel unsupervised domain adaptation framework based on domain-specific batch normalization in deep neural networks. We aim to adapt to both domains by specializing batch normalization layers in convolutional neural networks while allowing them to share all other model parameters, which is realized by a two-stage algorithm. In the first stage, we estimate pseudo-labels for the examples in the target domain using an external unsupervised domain adaptation algorithm---for example, MSTN or CPUA---integrating the proposed domain-specific batch normalization. The second stage learns th…
Variance reduction techniques are popular in accelerating gradient descent and stochastic gradient descent for optimization problems defined on both Euclidean space and Riemannian manifold. In this paper, we further improve on existing variance reduction methods for non-convex Riemannian optimization, including R-SVRG and R-SRG/R-SPIDER with batch size adaptation. We show that this strategy can achieve lower total complexities for optimizing both general non-convex and gradient dominated functions under both finite-sum and online settings. As a result, we also provide simpler convergence analy…
Norwegian University of Science and Technology（挪威科技大学）
Time series forecasting is an important problem, with many real world applications. Ensembles of deep neural networks have recently achieved impressive forecasting accuracy, but such large ensembles are impractical in many real world settings. Transformer models been successfully applied to a diverse set of challenging problems. We propose a novel adaptation of the original Transformer architecture focusing on the task of time series forecasting, called Persistence Initialization. The model is initialized as a naive persistence model by using a multiplicative gating mechanism combined with a r…
Scheduling the batch size to increase is an effective strategy to control gradient noise when training deep neural networks. Current approaches implement scheduling heuristics that neglect structure within the optimization procedure, limiting their flexibility to the training dynamics and capacity to discern the impact of their adaptations on generalization. We introduce Arbiter as a new hyperparameter optimization algorithm to perform batch size adaptations for learnable scheduling heuristics using gradients from a meta-objective function, which overcomes previous heuristic constraints by enf…
Blue Well 8, LLC（Blue Well 8有限责任公司）；Pioneer Square Labs（先锋广场实验室）
Adapting a model to perform well on unforeseen data outside its training set is a common problem that continues to motivate new approaches. We demonstrate that application of batch normalization in the output layer, prior to softmax activation, results in improved generalization across visual data domains in a refined ResNet model. The approach adds negligible computational complexity yet outperforms many domain adaptation methods that explicitly learn to align data domains. We benchmark this technique on the Office-Home dataset and show that batch normalization is competitive with other leadi…
In this paper, we propose a novel domain adaptation method for the source-free setting. In this setting, we cannot access source data during adaptation, while unlabeled target data and a model pretrained with source data are given. Due to lack of source data, we cannot directly match the data distributions between domains unlike typical domain adaptation algorithms. To cope with this problem, we propose utilizing batch normalization statistics stored in the pretrained model to approximate the distribution of unobserved source data. Specifically, we fix the classifier part of the model during a…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；VinAI Research（VinAI研究院）
Mini-batch optimal transport (m-OT) has been widely used recently to deal with the memory issue of OT in large-scale applications. Despite their practicality, m-OT suffers from misspecified mappings, namely, mappings that are optimal on the mini-batch level but are partially wrong in the comparison with the optimal transportation plan between the original measures. Motivated by the misspecified mappings issue, we propose a novel mini-batch method by using partial optimal transport (POT) between mini-batch empirical measures, which we refer to as mini-batch partial optimal transport (m-POT). Le…
IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Robert Bosch LLC（罗伯特·博世有限责任公司）
Most predictive models assume that training and test data are generated from a stationary process. However, this assumption does not hold true in practice. In this paper, we consider the scenario of a gradual concept drift due to the underlying non-stationarity of the data source. While previous work has investigated this scenario under a supervised-learning and adaption conditions, few have addressed the common, real-world scenario when labels are only available during training. We propose a novel, iterative algorithm for unsupervised adaptation of predictive models. We show that the performa…
In recent years, large pre-trained Transformer-based language models have led to dramatic improvements in many natural language understanding tasks. To train these models with increasing sizes, many neural network practitioners attempt to increase the batch sizes in order to leverage multiple GPUs to improve training speed. However, increasing the batch size often makes the optimization more difficult, leading to slow convergence or poor generalization that can require orders of magnitude more training time to achieve the same model quality. In this paper, we explore the steepness of the loss …
Deep neural networks (DNN) have shown unprecedented success in various computer vision applications such as image classification and object detection. However, it is still a common annoyance during the training phase, that one has to prepare at least thousands of labeled images to fine-tune a network to a specific domain. Recent study (Tommasi et al. 2015) shows that a DNN has strong dependency towards the training dataset, and the learned features cannot be easily transferred to a different but relevant task without fine-tuning. In this paper, we propose a simple yet powerful remedy, called A…
Beyond Batch Learning: Global Awareness Enhanced Domain Adaptation
School of Aeronautics and Astronautics, Shanghai Jiao Tong University（上海交通大学航空航天学院）；LIRIS（利里研究所）；CNRS（法国国家科学研究中心）；Ecole Centrale de Lyon（里昂中央理工学院）；Institut Universitaire de France (IUF)（法国大学研究院）
Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controls
ELLIS Unit Linz, LIT AI Lab；Institute for Machine Learning, Johannes Kepler University Linz, Austria；Medical University Vienna；Clinical Research Center for Medical AI, Johannes Kepler University Linz, Austria
Current deep learning adaptive optimizer methods adjust the step magnitude of parameter updates by altering the effective learning rate used by each parameter. Motivated by the known inverse relation between batch size and learning rate on update step magnitudes, we introduce a novel training procedure that dynamically decides the dimension and the composition of the current update step. Our procedure, Dynamic Batch Adaptation (DBA) analyzes the gradients of every sample and selects the subset that best improves certain metrics such as gradient variance for each layer of the network. We presen…
pFedBBN: A Personalized Federated Test-Time Adaptation with Balanced Batch Normalization for Class-Imbalanced Data
Center for Computational & Data Sciences (CCDS)（计算与数据科学中心）；Independent University（独立大学）；University of Central Florida（中央佛罗里达大学）；Curtin University（Curtin大学）；Umeå University（乌梅拉大学）
Mila；Université de Montréal（蒙特利尔大学）；Imperial College London（帝国理工学院）；Microsoft Research（微软研究院）
Unsupervised domain transfer is the task of transferring or translating samples from a source distribution to a different target distribution. Current solutions unsupervised domain transfer often operate on data on which the modes of the distribution are well-matched, for instance have the same frequencies of classes between source and target distributions. However, these models do not perform well when the modes are not well-matched, as would be the case when samples are drawn independently from two different, but related, domains. This mode imbalance is problematic as generative adversarial …
From drift to adaptation to the failed ml model: Transfer Learning in Industrial MLOps
University College London（伦敦大学学院）；The Alan Turing Institute（艾伦·图灵研究所）；Univeristy of Engineering and Technology（工程与技术大学）；Sahiwal Coal Fired Power Plant（萨希瓦尔燃煤发电厂）
RIKEN Center for Advanced Intelligence Project (RIKEN AIP)（理化学研究所先进智能项目中心）；Advanced Telecommunications Research Institute International (ATR)（国际电气通信基础技术研究所）
Electroencephalography (EEG) provides access to neuronal dynamics non-invasively with millisecond resolution, rendering it a viable method in neuroscience and healthcare. However, its utility is limited as current EEG technology does not generalize well across domains (i.e., sessions and subjects) without expensive supervised re-calibration. Contemporary methods cast this transfer learning (TL) problem as a multi-source/-target unsupervised domain adaptation (UDA) problem and address it with deep learning or shallow, Riemannian geometry aware alignment methods. Both directions have, so far, fa…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；VinAI Research（VinAI研究院）；Monash University（莫纳什大学）
Mini-batch optimal transport (m-OT) has been successfully used in practical applications that involve probability measures with a very high number of supports. The m-OT solves several smaller optimal transport problems and then returns the average of their costs and transportation plans. Despite its scalability advantage, the m-OT does not consider the relationship between mini-batches which leads to undesirable estimation. Moreover, the m-OT does not approximate a proper metric between probability measures since the identity property is not satisfied. To address these problems, we propose a n…
Princeton University（普林斯顿大学）；Penn State University（宾夕法尼亚州立大学）
Recently, test-time adaptation (TTA) has been proposed as a promising solution for addressing distribution shifts. It allows a base model to adapt to an unforeseen distribution during inference by leveraging the information from the batch of (unlabeled) test data. However, we uncover a novel security vulnerability of TTA based on the insight that predictions on benign samples can be impacted by malicious samples in the same batch. To exploit this vulnerability, we propose Distribution Invading Attack (DIA), which injects a small fraction of malicious data into the test batch. DIA causes models…
Unifying Detection and Adaptation in Task-Free Continual Learning
School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）；The Hong Kong University of Science and Technology（香港科技大学）；Shandong University（山东大学）；Qilu Hospital of Shandong University（山东大学齐鲁医院）
Univ Lyon（里昂大学）；Ecole Centrale de Lyon（里昂中央理工学院）；CNRS（法国国家科学研究中心）；INSA Lyon（里昂国立应用科学学院）；Univ Claude Bernard Lyon 1（里昂第一大学克洛德·贝尔纳）；Univ Louis Lumière Lyon 2（里昂第二大学路易·卢米埃尔）；Thales LAS France（泰雷兹LAS法国公司）
Deep neural networks often fail to generalize outside of their training distribution, in particular when only a single data domain is available during training. While test-time adaptation has yielded encouraging results in this setting, we argue that, to reach further improvements, these approaches should be combined with training procedure modifications aiming to learn a more diverse set of patterns. Indeed, test-time adaptation methods usually have to rely on a limited representation because of the shortcut learning phenomenon: only a subset of the available predictive patterns is learned wi…
Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校贝克曼高级科学技术研究所）；Microsoft Research（微软研究院）
Histopathology is critical for the diagnosis of many diseases, including cancer. These protocols typically require pathologists to manually evaluate slides under a microscope, which is time-consuming and subjective, leading to interest in machine learning to automate analysis. However, computational techniques are limited by batch effects, where technical factors like differences in preparation protocol or scanners can alter the appearance of slides, causing models trained on one institution to fail when generalizing to others. Here, we propose a domain adaptation method that improves the gene…
University of Ulm（乌尔姆大学）；Ravensburg-Weingarten University of Applied Sciences（拉芬斯堡-魏恩加腾应用科学大学）；The University of Sydney（悉尼大学）
We present a novel algorithm for anomaly detection on very large datasets and data streams. The method, named EXPected Similarity Estimation (EXPoSE), is kernel-based and able to efficiently compute the similarity between new data points and the distribution of regular data. The estimator is formulated as an inner product with a reproducing kernel Hilbert space embedding and makes no assumption about the type or shape of the underlying data distribution. We show that offline (batch) learning with EXPoSE can be done in linear time and online (incremental) learning takes constant time per instan…
