We address the relative paucity of empirical testing of learning algorithms (of any type) by introducing a new public-domain, Modular, Optimal Learning Testing Environment (MOLTE) for Bayesian ranking and selection problem, stochastic bandits or sequential experimental design problems. The Matlab-based simulator allows the comparison of a number of learning policies (represented as a series of .m modules) in the context of a wide range of problems (each represented in its own .m module) which makes it easy to add new algorithms and new test problems. State-of-the-art policies and various problem classes are provided in the package. The choice of problems and policies is guided through a spreadsheet-based interface. Different graphical metrics are included. MOLTE is designed to be compatible with parallel computing to scale up from local desktop to clusters and clouds. We offer MOLTE as an easy-to-use tool for the research community that will make it possible to perform much more comprehensive testing, spanning a broader selection of algorithms and test problems. We demonstrate the capabilities of MOLTE through a series of comparisons of policies on a starter library of test problems. We also address the problem of tuning and constructing priors that have been largely overlooked in optimal learning literature. We envision MOLTE as a modest spur to provide researchers an easy environment to study interesting questions involved in optimal learning.
Recent advances in deep Reinforcement Learning (RL) have created unprecedented opportunities for intelligent automation, where a machine can autonomously learn an optimal policy for performing a given task. However, current deep RL algorithms predominantly specialize in a narrow range of tasks, are sample inefficient, and lack sufficient stability, which in turn hinder their industrial adoption. This article tackles this limitation by developing and testing a Hyper-Actor Soft Actor-Critic (HASAC) RL framework based on the notions of task modularization and transfer learning. The goal of the pr…
University of California, Berkeley（加州大学伯克利分校）；Princeton University（普林斯顿大学）
Many transfer problems require re-using previously optimal decisions for solving new tasks, which suggests the need for learning algorithms that can modify the mechanisms for choosing certain actions independently of those for choosing others. However, there is currently no formalism nor theory for how to achieve this kind of modular credit assignment. To answer this question, we define modular credit assignment as a constraint on minimizing the algorithmic mutual information among feedback signals for different decisions. We introduce what we call the modularity criterion for testing whether …
University of Waterloo（滑铁卢大学）；Carnegie Mellon University（卡内基梅隆大学）
In bandit multiple hypothesis testing, each arm corresponds to a different null hypothesis that we wish to test, and the goal is to design adaptive algorithms that correctly identify large set of interesting arms (true discoveries), while only mistakenly identifying a few uninteresting ones (false discoveries). One common metric in non-bandit multiple testing is the false discovery rate (FDR). We propose a unified, modular framework for bandit FDR control that emphasizes the decoupling of exploration and summarization of evidence. We utilize the powerful martingale-based concept of "e-processe…
Machine learning models usually assume i.i.d data during training and testing, but data and tasks in real world often change over time. To emulate the transient nature of real world, we propose a challenging but practical task: text classification in-the-wild, which introduces different non-stationary training/testing stages. Decomposing a complex task into modular components can enable robust generalisation under such non-stationary environment. However, current modular approaches in NLP do not take advantage of recent advances in parameter efficient tuning of pretrained language models. To c…
BMW Group（宝马集团）；Johannes Kepler University Linz（林茨约翰内斯·开普勒大学）；University of Applied Sciences Upper Austria（上奥地利应用科学大学）；University of Auckland（奥克兰大学）
OutlierDetection.jl is an open-source ecosystem for outlier detection in Julia. It provides a range of high-performance outlier detection algorithms implemented directly in Julia. In contrast to previous packages, our ecosystem enables the development highly-scalable outlier detection algorithms using a high-level programming language. Additionally, it provides a standardized, yet flexible, interface for future outlier detection algorithms and allows for model composition unseen in previous packages. Best practices such as unit testing, continuous integration, and code coverage reporting are e…
University of Toronto（多伦多大学）；Harvard University（哈佛大学）
Markov Chain Monte Carlo (MCMC) algorithms are a workhorse of probabilistic modeling and inference, but are difficult to debug, and are prone to silent failure if implemented naively. We outline several strategies for testing the correctness of MCMC algorithms. Specifically, we advocate writing code in a modular way, where conditional probability calculations are kept separate from the logic of the sampler. We discuss strategies for both unit testing and integration testing. As a running example, we show how a Python implementation of Gibbs sampling for a mixture of Gaussians model can be test…
From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing
Bradley Department of Electrical and Computer Engineering, Virginia Tech（弗吉尼亚理工大学电气与计算机工程系布雷拉德部门）；National Security Institute, Virginia Tech（弗吉尼亚理工大学国家安全研究所）
We study the problem usually referred to as group testing in the context of COVID-19. Given $n$ samples taken from patients, how should we select mixtures of samples to be tested, so as to maximize information and minimize the number of tests? We consider both adaptive and non-adaptive strategies, and take a Bayesian approach with a prior both for infection of patients and test errors. We start by proposing a mathematically principled objective, grounded in information theory. We then optimize non-adaptive optimization strategies using genetic algorithms, and leverage the mathematical framewor…
Singapore University of Technology and Design（新加坡科技设计大学）
The massive progress of machine learning has seen its application over a variety of domains in the past decade. But how do we develop a systematic, scalable and modular strategy to validate machine-learning systems? We present, to the best of our knowledge, the first approach, which provides a systematic test framework for machine-learning systems that accepts grammar-based inputs. Our OGMA approach automatically discovers erroneous behaviours in classifiers and leverages these erroneous behaviours to improve the respective models. OGMA leverages inherent robustness properties present in any w…
Indian Institute of Science（印度科学研究院）；University of Illinois Urbana-Champaign, Department of Computer Science（伊利诺伊大学厄巴纳-香槟分校计算机科学系）；University of Wisconsin（威斯康星大学）
University of Texas at Austin（德克萨斯大学奥斯汀分校）；IBM Research（IBM研究院）；University of Washington（华盛顿大学）
Given independent samples generated from the joint distribution $p(\mathbf{x},\mathbf{y},\mathbf{z})$, we study the problem of Conditional Independence (CI-Testing), i.e., whether the joint equals the CI distribution $p^{CI}(\mathbf{x},\mathbf{y},\mathbf{z})= p(\mathbf{z}) p(\mathbf{y}|\mathbf{z})p(\mathbf{x}|\mathbf{z})$ or not. We cast this problem under the purview of the proposed, provable meta-algorithm, "Mimic and Classify", which is realized in two-steps: (a) Mimic the CI distribution close enough to recover the support, and (b) Classify to distinguish the joint and the CI distribution.…
ETH Zurich（苏黎世联邦理工学院）；ETH Zürich（苏黎世联邦理工学院）；Rice University（莱斯大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；Amazon Web Services（亚马逊云科技）
We study the problem usually referred to as group testing in the context of COVID-19. Given n samples collected from patients, how should we select and test mixtures of samples to maximize information and minimize the number of tests? Group testing is a well-studied problem with several appealing solutions, but recent biological studies impose practical constraints for COVID-19 that are incompatible with traditional methods. Furthermore, existing methods use unnecessarily restrictive solutions, which were devised for settings with more memory and compute constraints than the problem at hand. T…
