/pdf/convex-analysisnoer-san-nojin-zhan-nituite-5dl2rbmoyr.pdf

Convex Analysisの二,三の進展について

Big Data applications are typically associated with systems involving large numbers of users, massive complex software systems, and large-scale heterogeneous computing and storage architectures. The construction of such systems involves many distributed design choices. The end products (e.g., recommendation systems, medical analysis tools, real-time game engines, speech recognizers) thus involve many tunable configuration parameters. These parameters are often specified and hard-coded into the software by various developers or teams. If optimized jointly, these parameters can result in significant improvements. Bayesian optimization is a powerful tool for the joint optimization of design choices that is gaining great popularity in recent years. It promises greater automation so as to increase both product quality and human productivity. This review paper introduces Bayesian optimization, highlights some of its methodological aspects, and showcases a wide range of applications.

/pdf/taking-the-human-out-of-the-loop-a-review-of-bayesian-4olcznoudw.pdf

Taking the Human Out of the Loop: A Review of Bayesian Optimization

A multi-armed bandit problem - or, simply, a bandit problem - is a sequential allocation problem defined by a set of actions. At each time step, a unit resource is allocated to an action and some observable payoff is obtained. The goal is to maximize the total payoff obtained in a sequence of allocations. The name bandit refers to the colloquial term for a slot machine (a "one-armed bandit" in American slang). In a casino, a sequential allocation problem is obtained when the player is facing many slot machines at once (a "multi-armed bandit"), and must repeatedly choose where to insert the next coin. Multi-armed bandit problems are the most basic examples of sequential decision problems with an exploration-exploitation trade-off. This is the balance between staying with the option that gave highest payoffs in the past and exploring new options that might give higher payoffs in the future. Although the study of bandit problems dates back to the 1930s, exploration-exploitation trade-offs arise in several modern applications, such as ad placement, website optimization, and packet routing. Mathematically, a multi-armed bandit is defined by the payoff process associated with each option. In this book, the focus is on two extreme cases in which the analysis of regret is particularly simple and elegant: independent and identically distributed payoffs and adversarial payoffs. Besides the basic setting of finitely many actions, it also analyzes some of the most important variants and extensions, such as the contextual bandit model. This monograph is an ideal reference for students and researchers with an interest in bandit problems.

Regret Analysis of Stochastic and Nonstochastic Multi-Armed Bandit Problems

Information Theory and Reliable Communication

We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop. It regularises the weights by minimising a compression cost, known as the variational free energy or the expected lower bound on the marginal likelihood. We show that this principled kind of regularisation yields comparable performance to dropout on MNIST classification. We then demonstrate how the learnt uncertainty in the weights can be used to improve generalisation in non-linear regression problems, and how this weight uncertainty can be used to drive the exploration-exploitation trade-off in reinforcement learning.

Weight Uncertainty in Neural Networks

The stochastic multi-armed bandit model is a simple abstraction that has proven useful in many different contexts in statistics and machine learning. Whereas the achievable limit in terms of regret minimization is now well known, our aim is to contribute to a better understanding of the performance in terms of identifying the m best arms. We introduce generic notions of complexity for the two dominant frameworks considered in the literature: fixed-budget and fixed-confidence settings. In the fixed-confidence setting, we provide the first known distribution-dependent lower bound on the complexity that involves information-theoretic quantities and holds when m ≥ 1 under general assumptions. In the specific case of two armed-bandits, we derive refined lower bounds in both the fixedcon fidence and fixed-budget settings, along with matching algorithms for Gaussian and Bernoulli bandit models. These results show in particular that the complexity of the fixed-budget setting may be smaller than the complexity of the fixed-confidence setting, contradicting the familiar behavior observed when testing fully specified alternatives. In addition, we also provide improved sequential stopping rules that have guaranteed error probabilities and shorter average running times. The proofs rely on two technical results that are of independent interest: a deviation lemma for self-normalized sums (Lemma 7) and a novel change of measure inequality for bandit models (Lemma 1).

/pdf/on-the-complexity-of-best-arm-identification-in-multi-armed-7ed20kt1lj.pdf

On the complexity of best-arm identification in multi-armed bandit models

Many problems, such as cognitive radio, parameter control of a scanning tunnelling microscope or internet advertisement, can be modelled as non-stationary bandit problems where the distributions of rewards changes abruptly at unknown time instants In this paper, we analyze two algorithms designed for solving this issue: discounted UCB (D-UCB) and sliding-window UCB (SW-UCB) We establish an upperbound for the expected regret by upper-bounding the expectation of the number of times suboptimal arms are played The proof relies on an interesting Hoeffding type inequality for self normalized deviations with a random number of summands We establish a lower-bound for the regret in presence of abrupt changes in the arms reward distributions We show that the discounted UCB and the sliding-window UCB both match the lower-bound up to a logarithmic factor Numerical simulations show that D-UCB and SW-UCB perform significantly better than existing soft-max methods like EXP3S

On upper-confidence bound policies for switching bandit problems

We consider structured multi-armed bandit problems based on the Generalized Linear Model (GLM) framework of statistics. For these bandits, we propose a new algorithm, called GLM-UCB. We derive finite time, high probability bounds on the regret of the algorithm, extending previous analyses developed for the linear bandits to the non-linear case. The analysis highlights a key difficulty in generalizing linear bandit algorithms to the non-linear case, which is solved in GLM-UCB by focusing on the reward space rather than on the parameter space. Moreover, as the actual effectiveness of current parameterized bandit algorithms is often poor in practice, we provide a tuning method based on asymptotic arguments, which leads to significantly better practical performance. We present two numerical experiments on real-world data that illustrate the potential of the GLM-UCB approach.

/pdf/parametric-bandits-the-generalized-linear-case-14ttnk92kl.pdf

Parametric Bandits: The Generalized Linear Case

Stochastic bandit problems have been analyzed from two different perspectives: a frequentist view, where the parameter is a deterministic unknown quantity, and a Bayesian approach, where the parameter is drawn from a prior distribution. 
We show in this paper that methods derived from this second perspective prove optimal when evaluated using the frequentist cumulated regret as a measure of performance. We give a general formulation for a class of Bayesian index policies that rely on quantiles of the posterior distribution. For binary bandits, we prove that the corresponding algorithm, termed Bayes-UCB, satisfies finite-time regret bounds that imply its asymptotic optimality. More generally, Bayes-UCB appears as an unifying framework for several variants of the UCB algorithm addressing different bandit problems (parametric multi-armed bandits, Gaussian bandits with unknown mean and variance, linear bandits). But the generality of the Bayesian approach makes it possible to address more challenging models. In particular, we show how to handle linear bandits with sparsity constraints by resorting to Gibbs sampling.

/pdf/on-bayesian-upper-confidence-bounds-for-bandit-problems-2ep199n5tb.pdf

On Bayesian Upper Confidence Bounds for Bandit Problems

We consider optimal sequential allocation in the context of the so-called stochastic multi-armed bandit model. We describe a generic index policy, in the sense of Gittins [J. R. Stat. Soc. Ser. B Stat. Methodol. 41 (1979) 148-177], based on upper confidence bounds of the arm payoffs computed using the Kullback-Leibler divergence. We consider two classes of distributions for which instances of this general idea are analyzed: the kl-UCB algorithm is designed for one-parameter exponential families and the empirical KL-UCB algorithm for bounded and finitely supported distributions. Our main contribution is a unified finite-time analysis of the regret of these algorithms that asymptotically matches the lower bounds of Lai and Robbins [Adv. in Appl. Math. 6 (1985) 4-22] and Burnetas and Katehakis [Adv. in Appl. Math. 17 (1996) 122-142], respectively. We also investigate the behavior of these algorithms when used with general bounded rewards, showing in particular that they provide significant improvements over the state-of-the-art.

Aurélien Garivier

Papers

On the complexity of best-arm identification in multi-armed bandit models

On upper-confidence bound policies for switching bandit problems

Parametric Bandits: The Generalized Linear Case

On Bayesian Upper Confidence Bounds for Bandit Problems

Kullback-Leibler upper confidence bounds for optimal sequential allocation