检索结果-内蒙古大学图书馆

Inference and Sampling for Archimax Copulas

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ng, Yuting Hasan, Ali Tarokh, Vahid Duke University United States

Understanding multivariate dependencies in both the bulk and the tails of a distribution is an important problem for many applications, such as ensuring algorithms are robust to observations that are infrequent but have devastating effects. Archimax copulas are a family of distributions endowed with a precise representation that allows simultaneous modeling of the bulk and the tails of a distribution. Rather than separating the two as is typically done in practice, incorporating additional information from the bulk may improve inference of the tails, where observations are limited. Building on the stochastic representation of Archimax copulas, we develop a non-parametric inference method and sampling algorithm. Our proposed methods, to the best of our knowledge, are the first that allow for highly flexible and scalable inference and sampling algorithms, enabling the increased use of Archimax copulas in practical settings. We experimentally compare to state-of-the-art density modeling techniques, and the results suggest that the proposed method effectively extrapolates to the tails while scaling to higher dimensional data. Our findings suggest that the proposed algorithms can be used in a variety of applications where understanding the interplay between the bulk and the tails of a distribution is necessary, such as healthcare and safety. © 2022, CC BY.

关键词： learning algorithms

On the Choice of Data for Efficient Training and Validation of End-to-End Driving Models

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Klingner, Marvin Müller, Konstantin Mirzaie, Mona Breitenstein, Jasmin Termöhlen, Jan-Aike Fingscheidt, Tim Technische Universität Braunschweig Braunschweig Germany

The emergence of data-driven machine learning (ML) has facilitated significant progress in many complicated tasks such as highly-automated driving. While much effort is put into improving the ML models and learning algorithms in such applications, little focus is put into how the training data and/or validation setting should be designed. In this paper we investigate the influence of several data design choices regarding training and validation of deep driving models trainable in an end-to-end fashion. Specifically, (i) we investigate how the amount of training data influences the final driving performance, and which performance limitations are induced through currently used mechanisms to generate training data. (ii) Further, we show by correlation analysis, which validation design enables the driving performance measured during validation to generalize well to unknown test environments. (iii) Finally, we investigate the effect of random seeding and non-determinism, giving insights which reported improvements can be deemed significant. Our evaluations using the popular CARLA simulator provide recommendations regarding data generation and driving route selection for an efficient future development of end-to-end driving models. Copyright © 2022, The Authors. All rights reserved.

关键词： learning algorithms

FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Albalak, Alon Tuan, Yi-Lin Jandaghi, Pegah Pryor, Connor Yoffe, Luke Ramachandran, Deepak Getoor, Lise Pujara, Jay Wang, William Yang University of California Santa Barbara United States University of Southern California United States University of California Santa Cruz United States Google Research United States

Task transfer, transferring knowledge contained in related tasks, holds the promise of reducing the quantity of labeled data required to fine-tune language models. Dialogue understanding encompasses many diverse tasks, yet task transfer has not been thoroughly studied in conversational AI. This work explores conversational task transfer by introducing FETA: a benchmark for FEw-sample TAsk transfer in open-domain dialogue. FETA contains two underlying sets of conversations upon which there are 10 and 7 tasks annotated, enabling the study of intra-dataset task transfer;task transfer without domain adaptation. We utilize three popular language models and three learning algorithms to analyze the transferability between 132 source-target task pairs and create a baseline for future work. We run experiments in the single- and multi-source settings and report valuable findings, e.g., most performance trends are model-specific, and span extraction and multiple-choice tasks benefit the most from task transfer. In addition to task transfer, FETA can be a valuable resource for future research into the efficiency and generalizability of pre-training datasets and model architectures, as well as for learning settings such as continual and multitask learning. © 2022, CC BY-SA.

关键词： learning algorithms

A Survey on Backdoor Attack and Defense in Natural Language Processing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sheng, Xuan Han, Zhaoyang Li, Piji Chang, Xiangmao Nanjing University of Aeronautics and Astronautics Nanjing China

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources being limited. In such a situation, training data and models are exposed to the public. As a result, attackers can manipulate the training process to inject some triggers into the model, which is called backdoor attack. Backdoor attack is quite stealthy and difficult to be detected because it has little inferior influence on the model's performance for the clean samples. To get a precise grasp and understanding of this problem, in this paper, we conduct a comprehensive review of backdoor attacks and defenses in the field of NLP. Besides, we summarize benchmark datasets and point out the open issues to design credible systems to defend against backdoor attacks. Copyright © 2022, The Authors. All rights reserved.

关键词： learning algorithms

Con-Detect: Detecting Adversarially Perturbed Natural Language Inputs to Deep Classifiers Through Holistic Analysis

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Ali, Hassan Khan, Muhammad Suleman AlGhadhban, Amer Alazmi, Meshari Alzamil, Ahmad Al-Utaibi, Khaled Qadir, Junaid IHSAN Lab Information Technology University Lahore Pakistan Department of Electrical Engineering College of Engineering University of Ha’il Saudi Arabia Department of Information and Computer Science College of Computer Science and Engineering University of Ha’il Saudi Arabia Department of Computer Engineering College of Computer Science and Engineering University of Ha’il Saudi Arabia

Deep learning (DL) algorithms have shown wonders in many Natural Language Processing (NLP) tasks such as language-to-language translation, spam filtering, fake-news detection, and comprehension understanding. However, research has shown that the adversarial vulnerabilities of deep learning networks manifest themselves when DL is used for NLP tasks. Most mitigation techniques proposed to date are supervised—relying on adversarial retraining to improve the robustness—which is impractical. This work introduces a novel, unsupervised detection methodology for detecting adversarial inputs to NLP classifiers. In summary, we note that minimally perturbing an input to change a model’s output—a major strength of adversarial attacks—is a weakness that leaves unique statistical marks reflected in the cumulative contribution scores of the input. Particularly, we show that the cumulative contribution score, called CF-score, of adversarial inputs is generally greater than that of the clean inputs. We thus propose Con-Detect—a Contribution based Detection method—for detecting adversarial attacks against NLP classifiers. Con-Detect can be deployed with any classifier without having to retrain it. We experiment with multiple attackers—Text-bugger, Text-fooler, PWWS—on several architectures—MLP, CNN, LSTM, Hybrid CNN-RNN, BERT—trained for different classification tasks—IMDB sentiment classification, fake-news classification, AG news topic classification—under different threat models—Con-Detectblind attacks, Con-Detect-aware attacks, and Con-Detect-adaptive attacks—and show that Con-Detect can reduce the attack success rate (ASR) of different attacks from 100% to as low as 0% for the best cases and ≈70% for the worst case. Even in the worst case, we note a 100% increase in the required number of queries and a 50% increase in the number of words perturbed, suggesting that Con-Detect is hard to evade. © 2022, CC BY.

关键词： learning algorithms

Impossibility of Collective Intelligence

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Muandet, Krikamol Max Planck Institute for Intelligent Systems Tübingen Germany

Democratization of AI involves training and deploying machine learning models across heterogeneous and potentially massive environments. Diversity of data opens up a number of possibilities to advance AI systems, but also introduces pressing concerns such as privacy, security, and equity that require special attention. This work shows that it is theoretically impossible to design a rational learning algorithm that has the ability to successfully learn across heterogeneous environments, which we decoratively call collective intelligence (CI). By representing learning algorithms as choice correspondences over a hypothesis space, we are able to axiomatize them with essential properties. Unfortunately, the only feasible algorithm compatible with all of the axioms is the standard empirical risk minimization (ERM) which learns arbitrarily from a single environment. Our impossibility result reveals informational incomparability between environments as one of the foremost obstacles for researchers who design novel algorithms that learn from multiple environments, which sheds light on prerequisites for success in critical areas of machine learning such as out-of-distribution generalization, federated learning, algorithmic fairness, and multi-modal learning. © 2022, CC BY.

关键词： learning algorithms

CONVERGENCE OF FINITE MEMORY Q-learning FOR POMDPS AND NEAR OPTIMALITY OF LEARNED POLICIES UNDER FILTER STABILITY

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kara, Ali Devran Yüksel, Serdar The Department of Mathematics University of Michigan Ann ArborMI United States The Department of Mathematics and Statistics Queen’s University KingstonON Canada

In this paper, for POMDPs, we provide the convergence of a Q learning algorithm for control policies using a finite history of past observations and control actions, and, consequentially, we establish near optimality of such limit Q functions under explicit filter stability conditions. We present explicit error bounds relating the approximation error to the length of the finite history window. We establish the convergence of such Q-learning iterations under mild ergodicity assumptions on the state process during the exploration phase. We further show that the limit fixed point equation gives an optimal solution for an approximate belief-MDP. We then provide bounds on the performance of the policy obtained using the limit Q values compared to the performance of the optimal policy for the POMDP, where we also present explicit conditions using recent results on filter stability in controlled POMDPs. While there exist many experimental results, (i) the rigorous asymptotic convergence (to an approximate MDP value function) for such finite-memory Q-learning algorithms, and (ii) the near optimality with an explicit rate of convergence (in the memory size) under filter stability are results that are new to the literature, to our knowledge. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

Adversarial Cheap Talk

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lu, Chris Willi, Timon Letcher, Alistair Foerster, Jakob FLAIR University of Oxford United Kingdom aletcher.github.io

Adversarial attacks in reinforcement learning (RL) often assume highly-privileged access to the victim’s parameters, environment, or data. Instead, this paper proposes a novel adversarial setting called a Cheap Talk MDP in which an Adversary can merely append deterministic messages to the Victim’s observation, resulting in a minimal range of influence. The Adversary cannot occlude ground truth, influence underlying environment dynamics or reward signals, introduce non-stationarity, add stochasticity, see the Victim’s actions, or access their parameters. Additionally, we present a simple meta-learning algorithm called Adversarial Cheap Talk (ACT) to train Adversaries in this setting. We demonstrate that an Adversary trained with ACT still significantly influences the Victim’s training and testing performance, despite the highly constrained setting. Affecting train-time performance reveals a new attack vector and provides insight into the success and failure modes of existing RL algorithms. More specifically, we show that an ACT Adversary is capable of harming performance by interfering with the learner’s function approximation, or instead helping the Victim’s performance by outputting useful features. Finally, we show that an ACT Adversary can manipulate messages during train-time to directly and arbitrarily control the Victim at test-time. Project video and code are available at https://***/view/adversarial-cheap-talk. © 2022, CC BY.

关键词： learning algorithms

Tracking Error learning Control for precise mobile robot path tracking in outdoor environment

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kayacan, Erkan Chowdhary, Girish Senseable City Laboratory Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology United States Coordinated Science Laboratory Distributed Autonomous Systems Laboratory University of Illinois at Urbana-Champaign United States

This paper presents a Tracking-Error learning Control (TELC) algorithm for precise mobile robot path tracking in off-road terrain. In traditional tracking error-based control approaches, feedback and feedforward controllers are designed based on the nominal model which cannot capture the uncertainties, disturbances and changing working conditions so that they cannot ensure precise path tracking performance in the outdoor environment. In TELC algorithm, the feedforward control actions are updated by using the tracking error dynamics and the plant-model mismatch problem is thus discarded. Therefore, the feedforward controller gradually eliminates the feedback controller from the control of the system once the mobile robot has been on-track. In addition to the proof of the stability, it is proven that the cost functions do not have local minima so that the coefficients in TELC algorithm guarantee that the global minimum is reached. The experimental results show that the TELC algorithm results in better path tracking performance than the traditional tracking error-based control method. The mobile robot controlled by TELC algorithm can track a target path precisely with less than 10 cm error in off-road terrain. © 2021, CC BY.

关键词： learning algorithms