Searcharxiv⌕ Search

arXiv subjects

Dean P. Foster

Publications and source records attributed to Dean P. Foster.

At least 19 recordsLinked to original sources
arXiv2026

Proper Calibeating

The classic concept of "calibrated forecasts" and its more recent refinement, "calibeating," are defined with respect to the standard quadratic scoring rule. We extend these notions to the class of $\textit{proper}$ scoring rules (for which the best forecast is the true distribution) and define $\textit{proper-calibration}$ and $\textit{proper-calibeating}$ by requiring the errors to converge to zero uniformly over all bounded proper scoring rules. We first establish that calibration always implies proper-calibration, whereas calibeating need not imply proper-calibeating. Second, we show how to guarantee proper-calibeating and proper-multicalibeating. Finally, we demonstrate the equivalence between proper-calibration and universal no regret when best replying to forecasts in decision-making under uncertainty.

econ.TH↗
arXiv2023

On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring

A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees, and how these considerations change as we move from few to many agents. We study this question in a general framework for interactive decision making with multiple agents, encompassing Markov games with function approximation and normal-form games with bandit feedback. We focus on equilibrium computation, in which a centralized learning algorithm aims to compute an equilibrium by controlling multiple agents that interact with an unknown environment. Our main contributions are: - We provide upper and lower bounds on the optimal sample complexity for multi-agent decision making based on a multi-agent generalization of the Decision-Estimation Coefficient, a complexity measure introduced by Foster et al. (2021) in the single-agent counterpart to our setting. Compared to the best results for the single-agent setting, our bounds have additional gaps. We show that no "reasonable" complexity measure can close these gaps, highlighting a striking separation between single and multiple agents. - We show that characterizing the statistical complexity for multi-agent decision making is equivalent to characterizing the statistical complexity of single-agent decision making, but with hidden (unobserved) rewards, a framework that subsumes variants of the partial monitoring problem. As a consequence, we characterize the statistical complexity for hidden-reward interactive decision making to the best extent possible. Building on this development, we provide several new structural results, including 1) conditions under which the statistical complexity of multi-agent decision making can be reduced to that of single-agent, and 2) conditions under which the so-called curse of multiple agents can be avoided.

cs.LG↗
arXiv2022

Deep Inventory Management

This work provides a Deep Reinforcement Learning approach to solving a periodic review inventory control system with stochastic vendor lead times, lost sales, correlated demand, and price matching. While this dynamic program has historically been considered intractable, our results show that several policy learning approaches are competitive with or outperform classical methods. In order to train these algorithms, we develop novel techniques to convert historical data into a simulator. On the theoretical side, we present learnability results on a subclass of inventory control problems, where we provide a provable reduction of the reinforcement learning problem to that of supervised learning. On the algorithmic side, we present a model-based reinforcement learning procedure (Direct Backprop) to solve the periodic review inventory control problem by constructing a differentiable simulator. Under a variety of metrics Direct Backprop outperforms model-free RL and newsvendor baselines, in both simulations and real-world deployments.

cs.LG↗
arXiv2022

Linear Reinforcement Learning with Ball Structure Action Space

We study the problem of Reinforcement Learning (RL) with linear function approximation, i.e. assuming the optimal action-value function is linear in a known $d$-dimensional feature mapping. Unfortunately, however, based on only this assumption, the worst case sample complexity has been shown to be exponential, even under a generative model. Instead of making further assumptions on the MDP or value functions, we assume that our action space is such that there always exist playable actions to explore any direction of the feature space. We formalize this assumption as a ``ball structure'' action space, and show that being able to freely explore the feature space allows for efficient RL. In particular, we propose a sample-efficient RL algorithm (BallRL) that learns an $ε$-optimal policy using only $\tilde{O}\left(\frac{H^5d^3}{ε^3}\right)$ number of trajectories.

cs.LG↗
arXiv2022

Smooth Calibration, Leaky Forecasts, Finite Recall, and Nash Dynamics

We propose to smooth out the calibration score, which measures how good a forecaster is, by combining nearby forecasts. While regular calibration can be guaranteed only by randomized forecasting procedures, we show that smooth calibration can be guaranteed by deterministic procedures. As a consequence, it does not matter if the forecasts are leaked, i.e., made known in advance: smooth calibration can nevertheless be guaranteed (while regular calibration cannot). Moreover, our procedure has finite recall, is stationary, and all forecasts lie on a finite grid. To construct the procedure, we deal also with the related setups of online linear regression and weak calibration. Finally, we show that smooth calibration yields uncoupled finite-memory dynamics in n-person games "smooth calibrated learning" in which the players play approximate Nash equilibria in almost all periods (by contrast, calibrated learning, which uses regular calibration, yields only that the time-averages of play are approximate correlated equilibria).

econ.TH↗
arXiv2022

Forecast Hedging and Calibration

Calibration means that forecasts and average realized frequencies are close. We develop the concept of forecast hedging, which consists of choosing the forecasts so as to guarantee that the expected track record can only improve. This yields all the calibration results by the same simple basic argument while differentiating between them by the forecast-hedging tools used: deterministic and fixed point based versus stochastic and minimax based. Additional contributions are an improved definition of continuous calibration, ensuing game dynamics that yield Nash equilibria in the long run, and a new calibrated forecasting procedure for binary events that is simpler than all known such procedures.

econ.TH↗
arXiv2022

"Calibeating": Beating Forecasters at Their Own Game

In order to identify expertise, forecasters should not be tested by their calibration score, which can always be made arbitrarily small, but rather by their Brier score. The Brier score is the sum of the calibration score and the refinement score; the latter measures how good the sorting into bins with the same forecast is, and thus attests to "expertise." This raises the question of whether one can gain calibration without losing expertise, which we refer to as "calibeating." We provide an easy way to calibeat any forecast, by a deterministic online procedure. We moreover show that calibeating can be achieved by a stochastic procedure that is itself calibrated, and then extend the results to simultaneously calibeating multiple procedures, and to deterministic procedures that are continuously calibrated.

econ.TH↗
arXiv2022

A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation

The current paper studies sample-efficient Reinforcement Learning (RL) in settings where only the optimal value function is assumed to be linearly-realizable. It has recently been understood that, even under this seemingly strong assumption and access to a generative model, worst-case sample complexities can be prohibitively (i.e., exponentially) large. We investigate the setting where the learner additionally has access to interactive demonstrations from an expert policy, and we present a statistically and computationally efficient algorithm (Delphi) for blending exploration with expert queries. In particular, Delphi requires $\tilde{\mathcal{O}}(d)$ expert queries and a $\texttt{poly}(d,H,|\mathcal{A}|,1/\varepsilon)$ amount of exploratory samples to provably recover an $\varepsilon$-suboptimal policy. Compared to pure RL approaches, this corresponds to an exponential improvement in sample complexity with surprisingly-little expert input. Compared to prior imitation learning (IL) approaches, our required number of expert demonstrations is independent of $H$ and logarithmic in $1/\varepsilon$, whereas all prior work required at least linear factors of both in addition to the same dependence on $d$. Towards establishing the minimal amount of expert queries needed, we show that, in the same setting, any learner whose exploration budget is polynomially-bounded (in terms of $d,H,$ and $|\mathcal{A}|$) will require at least $\tildeΩ(\sqrt{d})$ oracle calls to recover a policy competing with the expert's value function. Under the weaker assumption that the expert's policy is linear, we show that the lower bound increases to $\tildeΩ(d)$.

cs.LG↗
arXiv2022

The Benefits of Implicit Regularization from SGD in Least Squares Problems

Stochastic gradient descent (SGD) exhibits strong algorithmic regularization effects in practice, which has been hypothesized to play an important role in the generalization of modern machine learning approaches. In this work, we seek to understand these issues in the simpler setting of linear regression (including both underparameterized and overparameterized regimes), where our goal is to make sharp instance-based comparisons of the implicit regularization afforded by (unregularized) average SGD with the explicit regularization of ridge regression. For a broad class of least squares problem instances (that are natural in high-dimensional settings), we show: (1) for every problem instance and for every ridge parameter, (unregularized) SGD, when provided with logarithmically more samples than that provided to the ridge algorithm, generalizes no worse than the ridge solution (provided SGD uses a tuned constant stepsize); (2) conversely, there exist instances (in this wide problem class) where optimally-tuned ridge regression requires quadratically more samples than SGD in order to have the same generalization performance. Taken together, our results show that, up to the logarithmic factors, the generalization performance of SGD is always no worse than that of ridge regression in a wide range of overparameterized problems, and, in fact, could be much better for some problem instances. More generally, our results show how algorithmic regularization has important consequences even in simpler (overparameterized) convex settings.

cs.LG↗
arXiv2022

Impartial Predictive Modeling and the Use of Proxy Variables

Fairness aware data mining (FADM) aims to prevent algorithms from discriminating against protected groups. The literature has come to an impasse as to what constitutes explainable variability as opposed to discrimination. This distinction hinges on a rigorous understanding of the role of proxy variables; i.e., those variables which are associated both the protected feature and the outcome of interest. We demonstrate that fairness is achieved by ensuring impartiality with respect to sensitive characteristics and provide a framework for impartiality by accounting for different perspectives on the data generating process. In particular, fairness can only be precisely defined in a full-data scenario in which all covariates are observed. We then analyze how these models may be conservatively estimated via regression in partial-data settings. Decomposing the regression estimates provides insights into previously unexplored distinctions between explainable variability and discrimination that illuminate the use of proxy variables in fairness aware data mining.

stat.ME↗
arXiv2021

On Submodular Contextual Bandits

We consider the problem of contextual bandits where actions are subsets of a ground set and mean rewards are modeled by an unknown monotone submodular function that belongs to a class $\mathcal{F}$. We allow time-varying matroid constraints to be placed on the feasible sets. Assuming access to an online regression oracle with regret $\mathsf{Reg}(\mathcal{F})$, our algorithm efficiently randomizes around local optima of estimated functions according to the Inverse Gap Weighting strategy. We show that cumulative regret of this procedure with time horizon $n$ scales as $O(\sqrt{n \mathsf{Reg}(\mathcal{F})})$ against a benchmark with a multiplicative factor $1/2$. On the other hand, using the techniques of (Filmus and Ward 2014), we show that an $ε$-Greedy procedure with local randomization attains regret of $O(n^{2/3} \mathsf{Reg}(\mathcal{F})^{1/3})$ against a stronger $(1-e^{-1})$ benchmark.

cs.LG↗
arXiv2021

Threshold Martingales and the Evolution of Forecasts

This paper introduces a martingale that characterizes two properties of evolving forecast distributions. Ideal forecasts of a future event behave as martingales, sequen- tially updating the forecast to leverage the available information as the future event approaches. The threshold martingale introduced here measures the proportion of the forecast distribution lying below a threshold. In addition to being calibrated, a threshold martingale has quadratic variation that accumulates to a total determined by a quantile of the initial forecast distribution. Deviations from calibration or to- tal volatility signal problems in the underlying model. Calibration adjustments are well-known, and we augment these by introducing a martingale filter that improves volatility while guaranteeing smaller mean squared error. Thus, post-processing can rectify problems with calibration and volatility without revisiting the original forecast- ing model. We apply threshold martingales first to forecasts from simulated models and then to models that predict the winner in professional basketball games.

cs.LG↗
arXiv2020

What are the Statistical Limits of Offline RL with Linear Function Approximation?

Offline reinforcement learning seeks to utilize offline (observational) data to guide the learning of (causal) sequential decision making strategies. The hope is that offline reinforcement learning coupled with function approximation methods (to deal with the curse of dimensionality) can provide a means to help alleviate the excessive sample complexity burden in modern sequential decision making problems. However, the extent to which this broader approach can be effective is not well understood, where the literature largely consists of sufficient conditions. This work focuses on the basic question of what are necessary representational and distributional conditions that permit provable sample-efficient offline reinforcement learning. Perhaps surprisingly, our main result shows that even if: i) we have realizability in that the true value function of \emph{every} policy is linear in a given set of features and 2) our off-policy data has good coverage over all features (under a strong spectral condition), then any algorithm still (information-theoretically) requires a number of offline samples that is exponential in the problem horizon in order to non-trivially estimate the value of \emph{any} given policy. Our results highlight that sample-efficient offline policy evaluation is simply not possible unless significantly stronger conditions hold; such conditions include either having low distribution shift (where the offline data distribution is close to the distribution of the policy to be evaluated) or significantly stronger representational conditions (beyond realizability).

cs.LG↗
arXiv2020

Fitting High-Dimensional Interaction Models with Error Control

There is a renewed interest in polynomial regression in the form of identifying influential interactions between features. In many settings, this takes place in a high-dimensional model, making the number of interactions unwieldy or computationally infeasible. Furthermore, it is difficult to analyze such spaces directly as they are often highly correlated. Standard feature selection issues remain such as how to determine a final model which generalizes well. This paper solves these problems with a sequential algorithm called Revisiting Alpha-Investing (RAI). RAI is motivated by the principle of marginality and searches the feature-space of higher-order interactions by greedily building upon lower-order terms. RAI controls a notion of false rejections and comes with a performance guarantee relative to the best-subset model. This ensures that signal is identified while providing a valid stopping criterion to prevent over-selection. We apply RAI in a novel setting over a family of regressions in order to select gene-specific interaction models for differential expression profiling.

stat.ME↗
arXiv2019

Coupled Recurrent Models for Polyphonic Music Composition

This paper introduces a novel recurrent model for music composition that is tailored to the structure of polyphonic music. We propose an efficient new conditional probabilistic factorization of musical scores, viewing a score as a collection of concurrent, coupled sequences: i.e. voices. To model the conditional distributions, we borrow ideas from both convolutional and recurrent neural models; we argue that these ideas are natural for capturing music's pitch invariances, temporal structure, and polyphony. We train models for single-voice and multi-voice composition on 2,300 scores from the KernScores dataset.

cs.SD↗
arXiv2016

Kernel ridge vs. principal component regression: minimax bounds and adaptability of regularization operators

Regularization is an essential element of virtually all kernel methods for nonparametric regression problems. A critical factor in the effectiveness of a given kernel method is the type of regularization that is employed. This article compares and contrasts members from a general class of regularization techniques, which notably includes ridge regression and principal component regression. We derive an explicit finite-sample risk bound for regularization-based estimators that simultaneously accounts for (i) the structure of the ambient function space, (ii) the regularity of the true regression function, and (iii) the adaptability (or qualification) of the regularization. A simple consequence of this upper bound is that the risk of the regularization-based estimators matches the minimax rate in a variety of settings. The general bound also illustrates how some regularization techniques are more adaptable than others to favorable regularity properties that the true regression function may possess. This, in particular, demonstrates a striking difference between kernel ridge regression and kernel principal component regression. Our theoretical results are supported by numerical experiments.

math.ST↗
arXiv2016

Submodularity in Statistics: Comparing the Success of Model Selection Methods

We demonstrate the usefulness of submodularity in statistics as a characterization of the difficulty of the \emph{search} problem of feature selection. The search problem is the ability of a procedure to identify an informative set of features as opposed to the performance of the optimal set of features. Submodularity arises naturally in this setting due to its connection to combinatorial optimization. In statistics, submodularity isolates cases in which collinearity makes the choice of model features difficult from those in which this task is routine. Researchers often report the signal-to-noise ratio to measure the difficulty of simulated data examples. A measure of submodularity should also be provided as it characterizes an independent component difficulty. Furthermore, it is closely related to other statistical assumptions used in the development of the Lasso, Dantzig selector, and sure information screening.

math.ST↗