arXiv research

Proposes resilience metrics for large blackout costs with logarithmic resilience.

The paper explores the geometric structure of cost functions in multiple dimensions.

Paper proposes efficient cost functions for automated market makers in DeFi.

We study the problem of regret minimization for distributed bandits learning, in which $M$ agents work collaboratively to minimize their total regret under the coordination of a central server. Our goal is to design communication protocols with near-optimal regret and little communication cost, which is measured by the…

Paper proposes FedQ-Advantage for federated Q-learning with near-optimal regret and low communication cost.

New algorithm reduces switching costs in RL beyond linear MDPs.

We introduce a new algorithm for online linear-quadratic control in a known system subject to adversarial disturbances. Existing regret bounds for this setting scale as $\sqrt{T}$ unless strong stochastic assumptions are imposed on the disturbance process. We give the first algorithm with logarithmic regret for arbitra…

New RL algorithms reduce costs for single-agent and federated learning.

New algorithms improve causal graph discovery with adaptive interventions, even under worst-case interventional costs.

A new UCB policy improves reward-cost ratio estimation in budgeted MAB.

New batched Langevin Thompson Sampling reduces communication costs for sequential decision making.

We study the problem of adaptive control of a high dimensional linear quadratic (LQ) system. Previous work established the asymptotic convergence to an optimal controller for various adaptive control schemes. More recently, for the average cost LQ problem, a regret bound of ${O}(\sqrt{T})$ was shown, apart form logarit…

Federated Q-Learning achieves linear regret speedup with low communication cost.

There are many industrial situations where rods are used to stir a fluid, or where rods repeatedly stretch a material such as bread dough or taffy. The goal in these applications is to stretch either material lines (in a fluid) or the material itself (for dough or taffy) as rapidly as possible. The growth rate of mater…

We study contextual bandits with budget and time constraints, referred to as constrained contextual bandits.The time and budget constraints significantly complicate the exploration and exploitation tradeoff because they introduce complex coupling among contexts over time.Such coupling effects make it difficult to obtai…

We consider the problem of optimizing the expected logarithmic utility of the value of a portfolio in a binomial model with proportional transaction costs with a long time horizon. By duality methods, we can find expressions for the boundaries of the no-trade-region and the asymptotic optimal growth rate, which can be …

The paper analyzes the statistical cost of tuning kernel hyperparameters in robust regression.

Oracle-efficient algorithms reduce combinatorial semi-bandit regret to logarithmic time.

Develops a new option pricing model under G-expectation framework.

This paper focuses on projection-free methods for solving smooth Online Convex Optimization (OCO) problems. Existing projection-free methods either achieve suboptimal regret bounds or have high per-iteration computational costs. To fill this gap, two efficient projection-free online methods called ORGFW and MORGFW are …

The dueling bandit is a learning framework wherein the feedback information in the learning process is restricted to a noisy comparison between a pair of actions. In this research, we address a dueling bandit problem based on a cost function over a continuous space. We propose a stochastic mirror descent algorithm and …

This work concerns estimation of multidimensional nonlinear regression models using multilayer perceptron (MLP). The main problem with such model is that we have to know the covariance matrix of the noise to get optimal estimator. however we show that, if we choose as cost function the logarithm of the determinant of t…

New algorithm for multi-fidelity bandits reduces costs and improves regret.

New method reduces total cost constraints in CBwK to sqrt(T) with fairness application.

We consider the Brownian market model and the problem of expected utility maximization of terminal wealth. We, specifically, examine the problem of maximizing the utility of terminal wealth under the presence of transaction costs of a fund/agent investing in futures markets. We offer some preliminary remarks about stat…

In frictionless markets, utility maximization problems are typically solved either by stochastic control or by martingale methods. Beginning with the seminal paper of Davis and Norman [Math. Oper. Res. 15 (1990) 676--713], stochastic control theory has also been used to solve various problems of this type in the presen…

Study shows sample complexity for learning optimal policies in SSP with generative model.

Paper optimizes multi-fidelity function with fast learning rates.

Algorithm achieves logarithmic regret with sublinear hints.

Investigates how rebalancing frequency and transaction costs affect log-optimal portfolios.

Paper proposes an $ε$-policy gradient for online pricing, reducing regret to $\mathcal{O}(\sqrt{T})$.

This work concerns testing the number of parameters in one hidden layer multilayer perceptron (MLP). For this purpose we assume that we have identifiable models, up to a finite group of transformations on the weights, this is for example the case when the number of hidden units is know. In this framework, we show that …

We present a formal model of human decision-making in explore-exploit tasks using the context of multi-armed bandit problems, where the decision-maker must choose among multiple options with uncertain rewards. We address the standard multi-armed bandit problem, the multi-armed bandit problem with transition costs, and …

Sharp 2-Wasserstein bounds for DDPMs derived from Föllmer process.

Paper proposes a method to solve log-optimal portfolios under ambiguous return distributions.

We estimate risk measures in Markov cost processes with lower and upper bounds.

Recently, prediction markets have shown considerable promise for developing flexible mechanisms for machine learning. In this paper, agents with isoelastic utilities are considered. It is shown that the costs associated with homogeneous markets of agents with isoelastic utilities produce equilibrium prices correspondin…

A distributed algorithm reduces communication cost in linear bandits to near-optimal levels.

Improved statistical inference for adaptive Thompson Sampling.

Despite their success, kernel methods suffer from a massive computational cost in practice. In this paper, in lieu of commonly used kernel expansion with respect to $N$ inputs, we develop a novel optimal design maximizing the entropy among kernel features. This procedure results in a kernel expansion with respect to en…

Due to the broad range of applications of stochastic multi-armed bandit model, understanding the effects of adversarial attacks and designing bandit algorithms robust to attacks are essential for the safe applications of this model. In this paper, we introduce a new class of attack named action-manipulation attack. In …

New bounds on adaptivity cost in stochastic optimization.

We revisit the problem of maximizing expected logarithmic utility from consumption over an infinite horizon in the Black-Scholes model with proportional transaction costs, as studied in the seminal paper of Davis and Norman [Math. Operation Research, 15, 1990]. Similarly to Kallsen and Muhle-Karbe [Ann. Appl. Probab., …

Novel compression method preserves privacy while reducing communication costs.

New algorithm balances exploration cost between groups in multi-armed bandits.

Linear-cost unbiased estimates for complex models via couplings.

In this paper, we investigate trading strategies based on exponential moving averages (ExpMAs) of an underlying risky asset. We study both logarithmic utility maximization and long-term growth rate maximization problems and find closed-form solutions when the drift of the underlying is modeled by either an Ornstein-Uhl…

A new algorithm reduces communication costs for collaborative decision-making across clients.