Performance optimization of deep learning models is conducted either manually or through automatic architecture search, or a combination of both. On the other hand, their performance strongly depends on the target hardware and how successfully the models were trained. We propose to use a multi-dimensional Pareto frontier to re-define the efficiency measure of candidate deep learning models, where several variables such as training cost, inference latency, and accuracy play a relative role in defining a dominant model. Furthermore, a random version of the multi-dimensional Pareto frontier is introduced to mitigate the uncertainty of accuracy, latency, and throughput of deep learning models in different experimental setups. These two complementary methods can be combined to perform objective benchmarking of deep learning models. Our proposed method is applied to a wide range of deep image classification models trained on ImageNet data. Our method combines competing variables with stochastic nature in a single relative efficiency measure. This allows ranking deep learning models that run efficiently on different hardware, and combining inference efficiency with training efficiency objectively.
This document contains supplementary material for the paper "Multi-objective Reinforcement Learning with Continuous Pareto Frontier Approximation", published at the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15). The paper is about learning a continuous approximation of the Pareto frontier in Multi-Objective Markov Decision Problems (MOMDPs). We propose a policy-based approach that exploits gradient information to generate solutions close to the Pareto ones. Differently from previous policy-gradient multi-objective algorithms, where n optimization routines are use to have n …
School of Software Engineering, South China University of Technology（华南理工大学软件学院）；Weixin Group, Tencent（腾讯微信事业群）；Tencent AI Lab, Tencent（腾讯AI实验室）
Designing feasible and effective architectures under diverse computation budgets incurred by different applications/devices is essential for deploying deep models in practice. Existing methods often perform an independent architecture search for each target budget, which is very inefficient yet unnecessary. Moreover, the repeated independent search manner would inevitably ignore the common knowledge among different search processes and hamper the search performance. To address these issues, we seek to train a general architecture generator that automatically produces effective architectures fo…
Given a multi-armed bandit problem it may be desirable to achieve a smaller-than-usual worst-case regret for some special actions. I show that the price for such unbalanced worst-case regret guarantees is rather high. Specifically, if an algorithm enjoys a worst-case regret of B with respect to some action, then there must exist another action for which the worst-case regret is at least Ω(nK/B), where n is the horizon and K the number of actions. I also give upper bounds in both the stochastic and adversarial settings showing that this result cannot be improved. For the stochastic case the par…
We present Parallel Feasible Pareto Frontier Entropy Search ($\{\text{PF}\}^2$ES) -- a novel information-theoretic acquisition function for multi-objective Bayesian optimization supporting unknown constraints and batch query. Due to the complexity of characterizing the mutual information between candidate evaluations and (feasible) Pareto frontiers, existing approaches must either employ crude approximations that significantly hamper their performance or rely on expensive inference schemes that substantially increase the optimization's computational overhead. By instead using a variational low…
We revisit the classical online portfolio selection problem. It is widely assumed that a trade-off between computational complexity and regret is unavoidable, with Cover's Universal Portfolios algorithm, SOFT-BAYES and ADA-BARRONS currently constituting its state-of-the-art Pareto frontier. In this paper, we present the first efficient algorithm, BISONS, that obtains polylogarithmic regret with memory and per-step running time requirements that are polynomial in the dimension, displacing ADA-BARRONS from the Pareto frontier. Additionally, we resolve a COLT 2020 open problem by showing that a c…
Rice University（莱斯大学）；University of Florida（佛罗里达大学）
Algorithmic fairness has emerged as an important consideration when using machine learning to make high-stakes societal decisions. Yet, improved fairness often comes at the expense of model accuracy. While aspects of the fairness-accuracy tradeoff have been studied, most work reports the fairness and accuracy of various models separately; this makes model comparisons nearly impossible without a model-agnostic metric that reflects the balance of the two desiderata. We seek to identify, quantify, and optimize the empirical Pareto frontier of the fairness-accuracy tradeoff. Specifically, we ident…
Osaka University（大阪大学）；Japan Fine Ceramics Center（日本精细陶瓷中心）；Nagoya Institute of Technology（名古屋工业大学）；National Institute for Material Science（国立材料科学研究所）
This paper studies an entropy-based multi-objective Bayesian optimization (MBO). The entropy search is successful approach to Bayesian optimization. However, for MBO, existing entropy-based methods ignore trade-off among objectives or introduce unreliable approximations. We propose a novel entropy-based MBO called Pareto-frontier entropy search (PFES) by considering the entropy of Pareto-frontier, which is an essential notion of the optimality of the multi-objective problem. Our entropy can incorporate the trade-off relation of the optimal values, and further, we derive an analytical formula w…
Recent progress in model selection raises the question of the fundamental limits of these techniques. Under specific scrutiny has been model selection for general contextual bandits with nested policy classes, resulting in a COLT2020 open problem. It asks whether it is possible to obtain simultaneously the optimal single algorithm guarantees over all policies in a nested sequence of policy classes, or if otherwise this is possible for a trade-off $α\in[\frac{1}{2},1)$ between complexity term and time: $\ln(|Π_m|)^{1-α}T^α$. We give a disappointing answer to this question. Even in the purely st…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）
Deploying machine learning (ML) models often requires both fairness and privacy guarantees. Both of these objectives present unique trade-offs with the utility (e.g., accuracy) of the model. However, the mutual interactions between fairness, privacy, and utility are less well-understood. As a result, often only one objective is optimized, while the others are tuned as hyper-parameters. Because they implicitly prioritize certain objectives, such designs bias the model in pernicious, undetectable ways. To address this, we adopt impartiality as a principle: design of ML pipelines should not favor…
A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontier
Shanghai Jiao Tong University（上海交通大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；University of Georgia（佐治亚大学）；New Jersey Institute of Technology（新泽西理工学院）
Massachusetts Institute of Technology（麻省理工学院）；The NSF AI Institute for Artificial Intelligence and Fundamental Interactions（美国国家科学基金会人工智能与基础交互研究所）
At the heart of both lossy compression and clustering is a trade-off between the fidelity and size of the learned representation. Our goal is to map out and study the Pareto frontier that quantifies this trade-off. We focus on the optimization of the Deterministic Information Bottleneck (DIB) objective over the space of hard clusterings. To this end, we introduce the primal DIB problem, which we show results in a much richer frontier than its previously studied Lagrangian relaxation when optimized over discrete search spaces. We present an algorithm for mapping out the Pareto frontier of the p…
Fraunhofer Center for Machine Learning（弗劳恩霍夫机器学习中心）；Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM（弗劳恩霍夫技术与经济数学研究所ITWM）
We present a novel adaptive optimization algorithm for black-box multi-objective optimization problems with binary constraints on the foundation of Bayes optimization. Our method is based on probabilistic regression and classification models, which act as a surrogate for the optimization goals and allow us to suggest multiple design points at once in each iteration. The proposed acquisition function is intuitively understandable and can be tuned to the demands of the problems at hand. We also present a novel ellipsoid truncation method to speed up the expected hypervolume calculation in a stra…
The Pennsylvania State University（宾夕法尼亚州立大学）；Microsoft Bing（微软必应）
As algorithmic decision-making systems are becoming more pervasive, it is crucial to ensure such systems do not become mechanisms of unfair discrimination on the basis of gender, race, ethnicity, religion, etc. Moreover, due to the inherent trade-off between fairness measures and accuracy, it is desirable to learn fairness-enhanced models without significantly compromising the accuracy. In this paper, we propose Pareto efficient Fairness (PEF) as a suitable fairness notion for supervised learning, that can ensure the optimal trade-off between overall loss and other fairness criteria. The propo…
What Is The Performance Ceiling of My Classifier? Utilizing Category-Wise Influence Functions for Pareto Frontier Analysis
Bellini College of AI, Cybersecurity, and Computing, University of South Florida（人工智能、网络安全与计算学院，佛罗里达州立大学）；Michtom School of Computer Science, Brandeis University（计算机科学学院，布兰迪斯大学）
We study the stochastic multi-player multi-armed bandit problem. In this problem, $m$ players cooperate to maximize their total reward from $K > m$ arms. However the players cannot communicate and are penalized (e.g. receive no reward) if they pull the same arm at the same time. We ask whether it is possible to obtain optimal instance-dependent regret $\tilde{O}(1/Δ)$ where $Δ$ is the gap between the $m$-th and $m+1$-st best arms. Such guarantees were recently achieved in a model allowing the players to implicitly communicate through intentional collisions. Surprisingly, we show that with no c…
YUKTI: From Natural-Language Situations to Robust, Verifiable Decisions An Uncertainty-Typed Proposition IR, Assumption-Robust Pareto Frontiers, and a Regret Certificate
The Offline-Frontier Shift: Diagnosing Distributional Limits in Generative Multi-Objective Optimization
LIT AI Lab and Institute for Machine Learning JKU Linz, Austria（LIT人工智能实验室和机器学习研究所，约翰·肯普夫大学（JKU）林茨分校，奥地利）；School of Computing, Engineering and Technology RGU, Aberdeen, Scotland（计算、工程与技术学院 RGU，阿伯丁，苏格兰）；Linz Center of Mechatronics GmbH Linz, Austria（林茨机电研究中心 GmbH，林茨，奥地利）
As multi-task models gain popularity in a wider range of machine learning applications, it is becoming increasingly important for practitioners to understand the fairness implications associated with those models. Most existing fairness literature focuses on learning a single task more fairly, while how ML fairness interacts with multiple tasks in the joint learning setting is largely under-explored. In this paper, we are concerned with how group fairness (e.g., equal opportunity, equalized odds) as an ML fairness concept plays out in the multi-task scenario. In multi-task learning, several ta…
The goal of lossy data compression is to reduce the storage cost of a data set $X$ while retaining as much information as possible about something ($Y$) that you care about. For example, what aspects of an image $X$ contain the most information about whether it depicts a cat? Mathematically, this corresponds to finding a mapping $X\to Z\equiv f(X)$ that maximizes the mutual information $I(Z,Y)$ while the entropy $H(Z)$ is kept below some fixed threshold. We present a method for mapping out the Pareto frontier for classification tasks, reflecting the tradeoff between retained entropy and class …
South China University of Technology（华南理工大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Tencent（腾讯）；University of Adelaide（阿德莱德大学）；Pazhou Laboratory（琶洲实验室）
Designing feasible and effective architectures under diverse computational budgets, incurred by different applications/devices, is essential for deploying deep models in real-world applications. To achieve this goal, existing methods often perform an independent architecture search process for each target budget, which is very inefficient yet unnecessary. More critically, these independent search processes cannot share their learned knowledge (i.e., the distribution of good architectures) with each other and thus often result in limited search results. To address these issues, we propose a Par…
Discovering novel materials can be greatly accelerated by iterative machine learning-informed proposal of candidates---active learning. However, standard \emph{global-scope error} metrics for model quality are not predictive of discovery performance, and can be misleading. We introduce the notion of \emph{Pareto shell-scope error} to help judge the suitability of a model for proposing material candidates. Further, through synthetic cases and a thermoelectric dataset, we probe the relation between acquisition function fidelity and active learning performance. Results suggest novel diagnostic to…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Oden Institute for Computational Engineering and Sciences（奥登计算工程与科学研究所）
Classification, recommendation, and ranking problems often involve competing goals with additional constraints (e.g., to satisfy fairness or diversity criteria). Such optimization problems are quite challenging, often involving non-convex functions along with considerations of user preferences in balancing trade-offs. Pareto solutions represent optimal frontiers for jointly optimizing multiple competing objectives. A major obstacle for frequently used linear-scalarization strategies is that the resulting optimization problem might not always converge to a global optimum. Furthermore, such meth…
University of California San Diego（加州大学圣迭戈分校）；Microsoft Research（微软研究院）；Microsoft（微软）
The Transformer architecture is ubiquitously used as the building block of large-scale autoregressive language models. However, finding architectures with the optimal trade-off between task performance (perplexity) and hardware constraints like peak memory utilization and latency is non-trivial. This is exacerbated by the proliferation of various hardware. We leverage the somewhat surprising empirical observation that the number of decoder parameters in autoregressive Transformers has a high rank correlation with task performance, irrespective of the architecture topology. This observation org…
