In recommender system or crowdsourcing applications of online learning, a human's preferences or abilities are often a function of the algorithm's recent actions. Motivated by this, a significant line of work has formalized settings where an action's loss is a function of the number of times that action was recently played in the prior $m$ timesteps, where $m$ corresponds to a bound on human memory capacity. To more faithfully capture decay of human memory with time, we introduce the Weighted Tallying Bandit (WTB), which generalizes this setting by requiring that an action's loss is a function of a \emph{weighted} summation of the number of times that arm was played in the last $m$ timesteps. This WTB setting is intractable without further assumption. So we study it under Repeated Exposure Optimality (REO), a condition motivated by the literature on human physiology, which requires the existence of an action that when repetitively played will eventually yield smaller loss than any other sequence of actions. We study the minimization of the complete policy regret (CPR), which is the strongest notion of regret, in WTB under REO. Since $m$ is typically unknown, we assume we only have access to an upper bound $M$ on $m$. We show that for problems with $K$ actions and horizon $T$, a simple modification of the successive elimination algorithm has $O \left( \sqrt{KT} + (m+M)K \right)$ CPR. Interestingly, upto an additive (in lieu of mutliplicative) factor in $(m+M)K$, this recovers the classical guarantee for the simpler stochastic multi-armed bandit with traditional regret. We additionally show that in our setting, any algorithm will suffer additive CPR of $\Omega \left( mK + M \right)$, demonstrating our result is nearly optimal. Our algorithm is computationally efficient, and we experimentally demonstrate its practicality and superiority over natural baselines.
相關內容
A sequence of random variables is called exchangeable if its joint distribution is invariant under permutations. The original formulation of de Finetti's theorem says that any exchangeable sequence of $\{0,1\}$-valued random variables can be thought of as a mixture of independent and identically distributed sequences in a certain precise mathematical sense. Interpreting this statement from a convex analytic perspective, Hewitt and Savage obtained the same conclusion for more general state spaces under some topological conditions. The main contribution of this paper is in providing a new framework that explains the theorem purely as a consequence of the underlying distribution of the random variables, with no topological conditions (beyond Hausdorffness) on the state space being necessary if the distribution is Radon. We also show that it is consistent with the axioms of ZFC that de Finetti's theorem holds for all sequences of exchangeable random variables taking values in any complete metric space. The framework we use is based on nonstandard analysis. We have provided a self-contained introduction to nonstandard analysis as an appendix, thus rendering measure theoretic probability and point-set topology as the only prerequisites for this paper. Our introduction aims to develop some new ideologies that might be of interest to mathematicians, philosophers, and mathematics educators alike. Our technical tools come from nonstandard topological measure theory, in which a highlight is a new generalization of Prokhorov's theorem. Modulo such technical tools, our proof relies on properties of the empirical measures induced by hyperfinitely many identically distributed random variables -- a feature that allows us to establish de Finetti's theorem in the generality that we seek while still retaining the combinatorial intuition of proofs of simpler versions of de Finetti's theorem.
Many asymptotically minimax procedures for function estimation often rely on somewhat arbitrary and restrictive assumptions such as isotropy or spatial homogeneity. This work enhances the theoretical understanding of Bayesian additive regression trees under substantially relaxed smoothness assumptions. We provide a comprehensive study of asymptotic optimality and posterior contraction of Bayesian forests when the regression function has anisotropic smoothness that possibly varies over the function domain. The regression function can also be possibly discontinuous. We introduce a new class of sparse {\em piecewise heterogeneous anisotropic} H\"{o}lder functions and derive their minimax lower bound of estimation in high-dimensional scenarios under the $L_2$-loss. We then find that the Bayesian tree priors, coupled with a Dirichlet subset selection prior for sparse estimation in high-dimensional scenarios, adapt to unknown heterogeneous smoothness, discontinuity, and sparsity. These results show that Bayesian forests are uniquely suited for more general estimation problems that would render other default machine learning tools, such as Gaussian processes, suboptimal. Our numerical study shows that Bayesian forests often outperform other competitors such as random forests and deep neural networks, which are believed to work well for discontinuous or complicated smooth functions. Beyond nonparametric regression, we also examined posterior contraction of Bayesian forests for density estimation and binary classification using the technique developed in this study.
We consider the problem of sequentially maximising an unknown function over a set of actions while ensuring that every sampled point has a function value below a given safety threshold. We model the function using kernel-based and Gaussian process methods, while differing from previous works in our assumption that the function is monotonically increasing with respect to a \emph{safety variable}. This assumption is motivated by various practical applications such as adaptive clinical trial design and robotics. Taking inspiration from the \textsc{\sffamily GP-UCB} and \textsc{\sffamily SafeOpt} algorithms, we propose an algorithm, monotone safe {\sffamily UCB} (\textsc{\sffamily M-SafeUCB}) for this task. We show that \textsc{\sffamily M-SafeUCB} enjoys theoretical guarantees in terms of safety, a suitably-defined regret notion, and approximately finding the entire safe boundary. In addition, we illustrate that the monotonicity assumption yields significant benefits in terms of the guarantees obtained, as well as algorithmic simplicity and efficiency. We support our theoretical findings by performing empirical evaluations on a variety of functions, including a simulated clinical trial experiment.
In recent years, online social networks have been the target of adversaries who seek to introduce discord into societies, to undermine democracies and to destabilize communities. Often the goal is not to favor a certain side of a conflict but to increase disagreement and polarization. To get a mathematical understanding of such attacks, researchers use opinion-formation models from sociology, such as the Friedkin--Johnsen model, and formally study how much discord the adversary can produce when altering the opinions for only a small set of users. In this line of work, it is commonly assumed that the adversary has full knowledge about the network topology and the opinions of all users. However, the latter assumption is often unrealistic in practice, where user opinions are not available or simply difficult to estimate accurately. To address this concern, we raise the following question: Can an attacker sow discord in a social network, even when only the network topology is known? We answer this question affirmatively. We present approximation algorithms for detecting a small set of users who are highly influential for the disagreement and polarization in the network. We show that when the adversary radicalizes these users and if the initial disagreement/polarization in the network is not very high, then our method gives a constant-factor approximation on the setting when the user opinions are known. To find the set of influential users, we provide a novel approximation algorithm for a variant of MaxCut in graphs with positive and negative edge weights. We experimentally evaluate our methods, which have access only to the network topology, and we find that they have similar performance as methods that have access to the network topology and all user opinions. We further present an NP-hardness proof, which was an open question by Chen and Racz [IEEE Trans. Netw. Sci. Eng., 2021].
Evaluating human exposure to environmental hazards is crucial for identifying susceptible communities and devising targeted health policies. Standard environmental hazard exposure assessment methods have been primarily based on place of residence, an approach which neglect individuals hazard exposures due to the daily life activities and mobility outside home neighborhood. To address this limitation, this study proposes a novel mobility-based index for hazard exposure evaluation. Using large-scale and fine-grained human mobility data, we quantify the extent of population dwell time in high-environmental-hazard places in 239 U.S. counties for three major environmental hazards: air pollution, heat, and toxic sites. Subsequently we explore the extent to which human mobility extends the reach of environmental hazards and also lead to the emergence of latent exposure for populations living outside high hazard areas with relatively considerable dwell time in high hazard areas. The findings help quantify environmental hazard exposure more reliably, considering the role of human mobility and activities. The interplay of spatial clustering in high-hazard regions and human movement trends creates environmental hazard traps intensifying exposure. Poor and ethnic minority residents disproportionately face multiple types of environmental hazards, aggravating potential health impacts. This data-driven evidence supports the severity of these injustices. We also studied latent exposure arising from visits outside residents' home areas, revealing millions population having 5% to10% of daily activities occur in high-exposure zones. Despite living in perceived safe areas, human mobility could expose millions of residents to different hazards. These findings provide crucial insights for targeted policies to mitigate these severe environmental injustices
We propose a family of recursive cutting-plane algorithms to solve feasibility problems with constrained memory, which can also be used for first-order convex optimization. Precisely, in order to find a point within a ball of radius $\epsilon$ with a separation oracle in dimension $d$ -- or to minimize $1$-Lipschitz convex functions to accuracy $\epsilon$ over the unit ball -- our algorithms use $\mathcal O(\frac{d^2}{p}\ln \frac{1}{\epsilon})$ bits of memory, and make $\mathcal O((C\frac{d}{p}\ln \frac{1}{\epsilon})^p)$ oracle calls, for some universal constant $C \geq 1$. The family is parametrized by $p\in[d]$ and provides an oracle-complexity/memory trade-off in the sub-polynomial regime $\ln\frac{1}{\epsilon}\gg\ln d$. While several works gave lower-bound trade-offs (impossibility results) -- we explicit here their dependence with $\ln\frac{1}{\epsilon}$, showing that these also hold in any sub-polynomial regime -- to the best of our knowledge this is the first class of algorithms that provides a positive trade-off between gradient descent and cutting-plane methods in any regime with $\epsilon\leq 1/\sqrt d$. The algorithms divide the $d$ variables into $p$ blocks and optimize over blocks sequentially, with approximate separation vectors constructed using a variant of Vaidya's method. In the regime $\epsilon \leq d^{-\Omega(d)}$, our algorithm with $p=d$ achieves the information-theoretic optimal memory usage and improves the oracle-complexity of gradient descent.
The B\"uhlmann model, a branch of classical credibility theory, has been successively applied to the premium estimation for group insurance contracts and other insurance specifications. In this paper, we develop a robust B\"uhlmann credibility via the censored version of loss data, or the censored mean (a robust alternative to traditional individual mean). This framework yields explicit formulas of structural parameters in credibility estimation for both scale-shape distribution families, location-scale distribution families, and their variants, which are commonly used to model insurance risks. The asymptotic properties of the proposed method are provided and corroborated through simulations, and their performance is compared to that of credibility based on the trimmed mean. By varying the censoring/trimming threshold level in several parametric models, we find all structural parameters via censoring are less volatile compared to the corresponding quantities via trimming, and using censored mean as a robust risk measure will reduce the influence of parametric loss assumptions on credibility estimation. Besides, the non-parametric estimations in credibility are discussed using the theory of $L-$estimators. And a numerical illustration from Wisconsin Local Government Property Insurance Fund indicates that the proposed robust credibility can prevent the effect caused by model mis-specification and capture the risk behavior of loss data in a broader viewpoint.
Decentralized multi-agent reinforcement learning (MARL) algorithms have become popular in the literature since it allows heterogeneous agents to have their own reward functions as opposed to canonical multi-agent Markov Decision Process (MDP) settings which assume common reward functions over all agents. In this work, we follow the existing work on collaborative MARL where agents in a connected time varying network can exchange information among each other in order to reach a consensus. We introduce vulnerabilities in the consensus updates of existing MARL algorithms where agents can deviate from their usual consensus update, who we term as adversarial agents. We then proceed to provide an algorithm that allows non-adversarial agents to reach a consensus in the presence of adversaries under a constrained setting.
We hypothesize that due to the greedy nature of learning in multi-modal deep neural networks, these models tend to rely on just one modality while under-fitting the other modalities. Such behavior is counter-intuitive and hurts the models' generalization, as we observe empirically. To estimate the model's dependence on each modality, we compute the gain on the accuracy when the model has access to it in addition to another modality. We refer to this gain as the conditional utilization rate. In the experiments, we consistently observe an imbalance in conditional utilization rates between modalities, across multiple tasks and architectures. Since conditional utilization rate cannot be computed efficiently during training, we introduce a proxy for it based on the pace at which the model learns from each modality, which we refer to as the conditional learning speed. We propose an algorithm to balance the conditional learning speeds between modalities during training and demonstrate that it indeed addresses the issue of greedy learning. The proposed algorithm improves the model's generalization on three datasets: Colored MNIST, Princeton ModelNet40, and NVIDIA Dynamic Hand Gesture.
Deep neural networks (DNNs) have become a proven and indispensable machine learning tool. As a black-box model, it remains difficult to diagnose what aspects of the model's input drive the decisions of a DNN. In countless real-world domains, from legislation and law enforcement to healthcare, such diagnosis is essential to ensure that DNN decisions are driven by aspects appropriate in the context of its use. The development of methods and studies enabling the explanation of a DNN's decisions has thus blossomed into an active, broad area of research. A practitioner wanting to study explainable deep learning may be intimidated by the plethora of orthogonal directions the field has taken. This complexity is further exacerbated by competing definitions of what it means ``to explain'' the actions of a DNN and to evaluate an approach's ``ability to explain''. This article offers a field guide to explore the space of explainable deep learning aimed at those uninitiated in the field. The field guide: i) Introduces three simple dimensions defining the space of foundational methods that contribute to explainable deep learning, ii) discusses the evaluations for model explanations, iii) places explainability in the context of other related deep learning research areas, and iv) finally elaborates on user-oriented explanation designing and potential future directions on explainable deep learning. We hope the guide is used as an easy-to-digest starting point for those just embarking on research in this field.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191