We present an approach to structured prediction from bandit feedback, called Bandit Structured Prediction, where only the value of a task loss function at a single predicted point, instead of a correct structure, is observed in learning. We present an application to discriminative reranking in Statistical Machine Translation (SMT) where the learning algorithm only has access to a 1-BLEU loss evaluation of a predicted translation instead of obtaining a gold standard reference translation. In our experiment bandit feedback is obtained by evaluating BLEU on reference translations without revealing them to the algorithm. This can be thought of as a simulation of interactive machine translation where an SMT system is personalized by a user who provides single point feedback to predicted translations. Our experiments show that our approach improves translation quality and is comparable to approaches that employ more informative feedback in learning.
Heidelberg University（海德堡大学）；Amazon Development Center（亚马逊开发中心）
The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system. A challenge arises by the fact that risk-averse commercial SMT systems deterministically log the most probable translation. The lack of sufficient exploration of the SMT output space seemingly contradicts the theoretical requirements for counterfactual learning. We show that counterfactual learning from deterministic bandit logs is possible nevertheless by smoothing ou…
Adapting machine translation systems in the real world is a difficult problem. In contrast to offline training, users cannot provide the type of fine-grained feedback (such as correct translations) typically used for improving the system. Moreover, different users have different translation needs, and even a single user's needs may change over time. In this work we take a different approach, treating the problem of adaptation as one of selection. Instead of adapting a single system, we train many translation systems using different architectures, datasets, and optimization methods. Using bandi…
Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear bandit learning to neural sequence-to-sequence learning problems using attention-based recurrent neural networks. Furthermore, we show how to incorporate control variates into our learning algorithms for variance reduction and improved generalization. We present an evaluation on a …
We describe the University of Maryland machine translation systems submitted to the WMT17 German-English Bandit Learning Task. The task is to adapt a translation system to a new domain, using only bandit feedback: the system receives a German sentence to translate, produces an English sentence, and only gets a scalar score as feedback. Targeting these two challenges (adaptation and bandit learning), we built a standard neural machine translation system and extended it in two ways: (1) robust reinforcement learning techniques to learn effectively from the bandit feedback, and (2) domain adaptat…
Training data for machine translation (MT) is often sourced from a multitude of large corpora that are multi-faceted in nature, e.g. containing contents from multiple domains or different levels of quality or complexity. Naturally, these facets do not occur with equal frequency, nor are they equally important for the test scenario at hand. In this work, we propose to optimize this balance jointly with MT model parameters to relieve system developers from manual schedule design. A multi-armed bandit is trained to dynamically choose between facets in a way that is most beneficial for the MT syst…
Carnegie Mellon University（卡内基梅隆大学）；Google Research（谷歌研究院）；DeepMind；Duke University（杜克大学）；Norwegian University of Science and Technology（挪威科技大学）
We propose a novel framework for structured bandits, which we call an influence diagram bandit. Our framework captures complex statistical dependencies between actions, latent variables, and observations; and thus unifies and extends many existing models, such as combinatorial semi-bandits, cascading bandits, and low-rank bandits. We develop novel online learning algorithms that learn to act efficiently in our models. The key idea is to track a structured posterior distribution of model parameters, either exactly or approximately. To act, we sample model parameters from their posterior and the…
Stochastic zeroth-order (SZO), or gradient-free, optimization allows to optimize arbitrary functions by relying only on function evaluations under parameter perturbations, however, the iteration complexity of SZO methods suffers a factor proportional to the dimensionality of the perturbed function. We show that in scenarios with natural sparsity patterns as in structured prediction applications, this factor can be reduced to the expected number of active features over input-output pairs. We give a general proof that applies sparse SZO optimization to Lipschitz-continuous, nonconvex, stochastic…
Heidelberg University（海德堡大学）；Tufts University（塔夫茨大学）；Amazon Development Center（亚马逊开发中心）
Stochastic structured prediction under bandit feedback follows a learning protocol where on each of a sequence of iterations, the learner receives an input, predicts an output structure, and receives partial feedback in form of a task loss evaluation of the predicted structure. We present applications of this learning scenario to convex and non-convex objectives for structured prediction and analyze them as stochastic first-order methods. We present an experimental evaluation on problems of natural language processing over exponential output spaces, and compare convergence speed across differe…
University of Maryland（马里兰大学）；Microsoft Research, New York（微软研究院纽约分院）
Machine translation is a natural candidate problem for reinforcement learning from human feedback: users provide quick, dirty ratings on candidate translations to guide a system to improve. Yet, current neural machine translation training focuses on expensive human-generated reference translations. We describe a reinforcement learning algorithm that improves neural machine translation systems from simulated human feedback. Our algorithm combines the advantage actor-critic algorithm (Mnih et al., 2016) with the attention-based neural encoder-decoder architecture (Luong et al., 2015). This algor…
Amazon Development Center Germany（亚马逊德国开发中心）；Heidelberg University（海德堡大学）
We introduce and describe the results of a novel shared task on bandit learning for machine translation. The task was organized jointly by Amazon and Heidelberg University for the first time at the Second Conference on Machine Translation (WMT 2017). The goal of the task is to encourage research on learning machine translation from weak user feedback instead of human references or post-edits. On each of a sequence of rounds, a machine translation system is required to propose a translation for an input, and receives a real-valued estimate of the quality of the proposed translation for learning…
Carnegie Mellon University（卡内基梅隆大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
We consider a finite-armed structured bandit problem in which mean rewards of different arms are known functions of a common hidden parameter $θ^*$. Since we do not place any restrictions of these functions, the problem setting subsumes several previously studied frameworks that assume linear or invertible reward functions. We propose a novel approach to gradually estimate the hidden $θ^*$ and use the estimate together with the mean reward functions to substantially reduce exploration of sub-optimal arms. This approach enables us to fundamentally generalize any classic bandit algorithm includi…
University of Alberta（阿尔伯塔大学）；INRIA（法国国家信息与自动化研究所）
We study a new type of K-armed bandit problem where the expected return of one arm may depend on the returns of other arms. We present a new algorithm for this general class of problems and show that under certain circumstances it is possible to achieve finite expected cumulative regret. We also give problem-dependent lower bounds on the cumulative regret showing that at least in special cases the new algorithm is nearly optimal.
We study the adversarial multi-armed bandit problem and create a completely online algorithmic framework that is invariant under arbitrary translations and scales of the arm losses. We study the expected performance of our algorithm against a generic competition class, which makes it applicable for a wide variety of problem scenarios. Our algorithm works from a universal prediction perspective and the performance measure used is the expected regret against arbitrary arm selection sequences, which is the difference between our losses and a competing loss sequence. The competition class can be d…
Multi-armed bandits are a quintessential machine learning problem requiring the balancing of exploration and exploitation. While there has been progress in developing algorithms with strong theoretical guarantees, there has been less focus on practical near-optimal finite-time performance. In this paper, we propose an algorithm for Bayesian multi-armed bandits that utilizes value-function-driven online planning techniques. Building on previous work on UCB and Gittins index, we introduce linearly-separable value functions that take both the expected return and the benefit of exploration into co…
Politecnico di Milano（米兰理工大学）；Facebook AI Research（脸书人工智能研究院）
We study finite-armed stochastic bandits where the rewards of each arm might be correlated to those of other arms. We introduce a novel phased algorithm that exploits the given structure to build confidence sets over the parameters of the true bandit problem and rapidly discard all sub-optimal arms. In particular, unlike standard bandit algorithms with no structure, we show that the number of times a suboptimal arm is selected may actually be reduced thanks to the information collected by pulling other arms. Furthermore, we show that, in some structures, the regret of an anytime extension of o…
Bandit learning algorithms typically involve the balance of exploration and exploitation. However, in many practical applications, worst-case scenarios needing systematic exploration are seldom encountered. In this work, we consider a smoothed setting for structured linear contextual bandits where the adversarial contexts are perturbed by Gaussian noise and the unknown parameter $θ^*$ has structure, e.g., sparsity, group sparsity, low rank, etc. We propose simple greedy algorithms for both the single- and multi-parameter (i.e., different parameter for each context) settings and provide a unifi…
This paper introduces and addresses a wide class of stochastic bandit problems where the function mapping the arm to the corresponding reward exhibits some known structural properties. Most existing structures (e.g. linear, Lipschitz, unimodal, combinatorial, dueling, ...) are covered by our framework. We derive an asymptotic instance-specific regret lower bound for these problems, and develop OSSB, an algorithm whose regret matches this fundamental limit. OSSB is not based on the classical principle of "optimism in the face of uncertainty" or on Thompson sampling, and rather aims at matching …
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Minnesota - Twin Cities（明尼苏达大学双城分校）
This paper studies the adversarial graphical contextual bandits, a variant of adversarial multi-armed bandits that leverage two categories of the most common side information: \emph{contexts} and \emph{side observations}. In this setting, a learning agent repeatedly chooses from a set of $K$ actions after being presented with a $d$-dimensional context vector. The agent not only incurs and observes the loss of the chosen action, but also observes the losses of its neighboring actions in the observation structures, which are encoded as a series of feedback graphs. This setting models a variety o…
The stochastic linear bandit problem proceeds in rounds where at each round the algorithm selects a vector from a decision set after which it receives a noisy linear loss parameterized by an unknown vector. The goal in such a problem is to minimize the (pseudo) regret which is the difference between the total expected loss of the algorithm and the total expected loss of the best fixed vector in hindsight. In this paper, we consider settings where the unknown parameter has structure, e.g., sparse, group sparse, low-rank, which can be captured by a norm, e.g., $L_1$, $L_{(1,2)}$, nuclear norm. W…
Tel Aviv University（特拉维夫大学）；Institute for Advanced Study（高等研究院）；Microsoft Research（微软研究院）；Università degli Studi di Milano（米兰大学）；University of Insubria（因苏布里亚大学）；Technion（以色列理工学院）；Weizmann Institute of Science（魏茨曼科学研究所）
We present and study a partial-information model of online learning, where a decision maker repeatedly chooses from a finite set of actions, and observes some subset of the associated losses. This naturally models several situations where the losses of different actions are related, and knowing the loss of one action provides information on the loss of other actions. Moreover, it generalizes and interpolates between the well studied full-information setting (where all losses are revealed) and the bandit setting (where only the loss of the action chosen by the player is revealed). We provide se…
Ateneo de Manila University（马尼拉雅典耀大学）；Heidelberg University（海德堡大学）
We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and analyze the influence of reliability on the learnability of a reward estimator, and the effect of the quality of reward estimates on the overall RL task. Our analysis of cardinal (5-point ratings) and ordinal (pairwise preferences) feedback shows that their intra- and inter-annotator $α$-agreement is comparable. Best reliability is obtained for standardized…
Otto von Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）
We investigate the problem dependent regime in the stochastic Thresholding Bandit problem (TBP) under several shape constraints. In the TBP, the objective of the learner is to output, at the end of a sequential game, the set of arms whose means are above a given threshold. The vanilla, unstructured, case is already well studied in the literature. Taking $K$ as the number of arms, we consider the case where (i) the sequence of arm's means $(μ_k)_{k=1}^K$ is monotonically increasing (MTBP) and (ii) the case where $(μ_k)_{k=1}^K$ is concave (CTBP). We consider both cases in the problem dependent …
We present the first real-world application of methods for improving neural machine translation (NMT) with human reinforcement, based on explicit and implicit user feedback collected on the eBay e-commerce platform. Previous work has been confined to simulation experiments, whereas in this paper we work with real logged feedback for offline bandit learning of NMT parameters. We conduct a thorough analysis of the available explicit user judgments---five-star ratings of translation quality---and show that they are not reliable enough to yield significant improvements in bandit learning. In contr…
The rich body of Bandit literature not only offers a diverse toolbox of algorithms, but also makes it hard for a practitioner to find the right solution to solve the problem at hand. Typical textbooks on Bandits focus on designing and analyzing algorithms, and surveys on applications often present a list of individual applications. While these are valuable resources, there exists a gap in mapping applications to appropriate Bandit algorithms. In this paper, we aim to reduce this gap with a structured map of Bandits to help practitioners navigate to find relevant and practical Bandit algorithms…
Mila, Université de Montréal（Mila（蒙特利尔大学））；McGill University（麦吉尔大学）；Mila, Université Laval（Mila（拉瓦尔大学））；Google Research（谷歌研究院）
We propose $\tt RandUCB$, a bandit strategy that builds on theoretically derived confidence intervals similar to upper confidence bound (UCB) algorithms, but akin to Thompson sampling (TS), it uses randomization to trade off exploration and exploitation. In the $K$-armed bandit setting, we show that there are infinitely many variants of $\tt RandUCB$, all of which achieve the minimax-optimal $\widetilde{O}(\sqrt{K T})$ regret after $T$ rounds. Moreover, for a specific multi-armed bandit setting, we show that both UCB and TS can be recovered as special cases of $\tt RandUCB$. For structured ban…
We study stochastic structured bandits for minimizing regret. The fact that the popular optimistic algorithms do not achieve the asymptotic instance-dependent regret optimality (asymptotic optimality for short) has recently alluded researchers. On the other hand, it is known that one can achieve bounded regret (i.e., does not grow indefinitely with $n$) in certain instances. Unfortunately, existing asymptotically optimal algorithms rely on forced sampling that introduces an $ω(1)$ term w.r.t. the time horizon $n$ in their regret, failing to adapt to the "easiness" of the instance. In this pape…
The addition of syntax-aware decoding in Neural Machine Translation (NMT) systems requires an effective tree-structured neural network, a syntax-aware attention model and a language generation model that is sensitive to sentence structure. We exploit a top-down tree-structured model called DRNN (Doubly-Recurrent Neural Networks) first proposed by Alvarez-Melis and Jaakola (2017) to create an NMT model called Seq2DRNN that combines a sequential encoder with tree-structured decoding augmented with a syntax-aware attention model. Unlike previous approaches to syntax-based NMT which use dependency…
Designers of statistical machine translation (SMT) systems have begun to employ tree-structured translation models. Systems involving tree-structured translation models tend to be complex. This article aims to reduce the conceptual complexity of such systems, in order to make them easier to design, implement, debug, use, study, understand, explain, modify, and improve. In service of this goal, the article extends the theory of semiring parsing to arrive at a novel abstract parsing algorithm with five functional parameters: a logic, a grammar, a semiring, a search strategy, and a termination co…
University of California, Davis（加州大学戴维斯分校）；Princeton University（普林斯顿大学）
Bandit algorithms have been predominantly analyzed in the convex setting with function-value based stationary regret as the performance measure. In this paper, motivated by online reinforcement learning problems, we propose and analyze bandit algorithms for both general and structured nonconvex problems with nonstationary (or dynamic) regret as the performance measure, in both stochastic and non-stochastic settings. First, for general nonconvex functions, we consider nonstationary versions of first-order and second-order stationary solutions as a regret measure, motivated by similar performanc…
Oregon State University（俄勒冈州立大学）；Baidu Research（百度研究院）
Beam search optimization resolves many issues in neural machine translation. However, this method lacks principled stopping criteria and does not learn how to stop during training, and the model naturally prefers the longer hypotheses during the testing time in practice since they use the raw score instead of the probability-based score. We propose a novel ranking method which enables an optimal beam search stopping criteria. We further introduce a structured prediction loss function which penalizes suboptimal finished candidates produced by beam search during training. Experiments of neural m…
Peking University（北京大学）；University of Minnesota（明尼苏达大学）；Microsoft Research（微软研究院）；Carnegie Mellon University（卡内基梅隆大学）
Consider a bandit algorithm that recommends actions to self-interested users in a recommendation system. The users are free to choose other actions and need to be incentivized to follow the algorithm's recommendations. While the users prefer to exploit, the algorithm can incentivize them to explore by leveraging the information collected from the previous users. All published work on this problem, known as incentivized exploration, focuses on small, unstructured action sets and mainly targets the case when the users' beliefs are independent across actions. However, realistic exploration proble…
Center for Language and Speech Processing（语言与语音处理中心）；Johns Hopkins University（约翰斯·霍普金斯大学）
Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper, we propose two simple search based curricula -- orderings of the multilingual training data -- which help improve translation performance in conjunction with existing techniques such as fine-tuning. Additionally, we attempt to learn a curriculum for MNMT from scratch jointly with the training of the translation system with the aid of contextual multi-arm bandits. We show on the FLORE…
In this paper, we investigate the use of linguistically motivated and computationally efficient structured language models for reranking N-best hypotheses in a statistical machine translation system. These language models, developed from Constraint Dependency Grammar parses, tightly integrate knowledge of words, morphological and lexical features, and syntactic dependency constraints. Two structured language models are applied for N-best rescoring, one is an almost-parsing language model, and the other utilizes more syntactic features by explicitly modeling syntactic dependencies between words…
Google Research（谷歌研究院）；Courant Institute（柯朗研究所）；Microsoft Corporation（微软公司）；Google Inc.（谷歌公司）；UC Santa Cruz（加州大学圣克鲁兹分校）
We study the problem of online path learning with non-additive gains, which is a central problem appearing in several applications, including ensemble structured prediction. We present new online algorithms for path learning with non-additive count-based gains for the three settings of full information, semi-bandit and full bandit with very favorable regret guarantees. A key component of our algorithms is the definition and computation of an intermediate context-dependent automaton that enables us to use existing algorithms designed for additive gains. We further apply our methods to the impor…
We consider sequential decision making under uncertainty, where the goal is to optimize over a large decision space using noisy comparative feedback. This problem can be formulated as a $K$-armed Dueling Bandits problem where $K$ is the total number of decisions. When $K$ is very large, existing dueling bandits algorithms suffer huge cumulative regret before converging on the optimal arm. This paper studies the dueling bandits problem with a large number of arms that exhibit a low-dimensional correlation structure. Our problem is motivated by a clinical decision making process in large decisio…
LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination
School of Computer Science and Engineering, Northeastern University, Shenyang, China（东北大学计算机科学与工程学院，中国沈阳）；NiuTrans Research, Shenyang, China（牛译研究院，中国沈阳）
University of Washington（华盛顿大学）；Tsinghua University（清华大学）；Peking University（北京大学）；Princeton University（普林斯顿大学）；Microsoft Research（微软研究院）
Bandit problems with linear or concave reward have been extensively studied, but relatively few works have studied bandits with non-concave reward. This work considers a large family of bandit problems where the unknown underlying reward function is non-concave, including the low-rank generalized linear bandit problems and two-layer neural network with polynomial activation bandit problem. For the low-rank generalized linear bandit problem, we provide a minimax-optimal algorithm in the dimension, refuting both conjectures in [LMT21, JWWN19]. Our algorithms are based on a unified zeroth-order o…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Microsoft Research（微软研究院）
A central problem in sequential decision making is to develop algorithms that are practical and computationally efficient, yet support the use of flexible, general-purpose models. Focusing on the contextual bandit problem, recent progress provides provably efficient algorithms with strong empirical performance when the number of possible alternatives ("actions") is small, but guarantees for decision making in large, continuous action spaces have remained elusive, leading to a significant gap between theory and practice. We present the first efficient, general-purpose algorithm for contextual b…
