A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New controller reduces regret in non-stochastic control with adversarial perturbations.
New algorithm achieves optimal regret in non-stochastic control, showing stochasticity is not beneficial.
Motivated by the task of hyperparameter optimization, we introduce the non-stochastic best-arm identification problem. Within the multi-armed bandit literature, the cumulative regret objective enjoys algorithms and analyses for both the non-stochastic and stochastic settings while to the best of our knowledge, the best…
New model for display advertising with stochastic and adversarial components.
New method tracks significant arm switches to improve bandit algorithms.
This paper studies a non-stochastic version of Fernholz's stochastic portfolio theory for a simple model of stock markets with continuous price paths. It establishes non-stochastic versions of the most basic results of stochastic portfolio theory and discusses connections with Stroock-Varadhan martingales.
Study optimal arms in combinatorial bandits with semi-bandit feedback and finite budget.
New algorithm controls linear systems with bandit feedback, achieving optimal regret.
Unified framework for analyzing online convex optimization across various settings.
New algorithm reduces decision switching in dynamic environments.
New algorithm controls systems with unknown, changing losses.
We consider a non-stochastic online learning approach to price financial options by modeling the market dynamic as a repeated game between the nature (adversary) and the investor. We demonstrate that such framework yields analogous structure as the Black-Scholes model, the widely popular option pricing model in stochas…
Overview of non-stochastic-gradient SA algorithms in signal processing and ML.
A new federated bandit problem with multiple adversaries, solved with a near-optimal algorithm.
New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.
Learning theory has largely focused on two main learning scenarios. The first is the classical statistical setting where instances are drawn i.i.d. from a fixed distribution and the second scenario is the online learning, completely adversarial scenario where adversary at every time step picks the worst instance to pro…
We present an extension of Monte Carlo Tree Search (MCTS) that strongly increases its efficiency for trees with asymmetry and/or loops. Asymmetric termination of search trees introduces a type of uncertainty for which the standard upper confidence bound (UCB) formula does not account. Our first algorithm (MCTS-T), whic…
Study finds optimal regret bound for multi-armed bandit problem with expert advice.
We consider the non-stochastic version of the (cooperative) multi-player multi-armed bandit problem. The model assumes no communication at all between the players, and furthermore when two (or more) players select the same action this results in a maximal loss. We prove the first -type regret guarantee for th…
We propose a framework to perform streaming covariance selection. Our approach employs regularization constraints where a time-varying sparsity parameter is iteratively estimated via stochastic gradient descent. This allows for the regularization parameter to be efficiently learnt in an online manner. The proposed fram…
We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal regret bounds. In the full-information setting, our results demonstrate that -differential privacy may be ensured for free -- in particular, the reg…
This paper makes a small step towards a non-stochastic version of superhedging duality relations in the case of one traded security with a continuous price path. Namely, we prove the coincidence of game-theoretic and measure-theoretic expectation for lower semicontinuous positive functionals. We consider a new broad de…
This work addresses the problem of regret minimization in non-stochastic multi-armed bandit problems, focusing on performance guarantees that hold with high probability. Such results are rather scarce in the literature since proving them requires a large deal of technical effort and significant modifications to the sta…
Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters. While recent approaches use Bayesian optimization to adaptively select configurations, we focus on speeding up random search through adaptive resource allocation and early-stopping. We formulate hyperparameter op…
Develops a new framework for conditional independence.
Improved privacy analysis for stochastic gradient descent.
Forré introduces a new conditional independence notion for mixed variables.
Optimal trading patterns adjust based on market efficiency and slippage costs.
We demonstrate that, in the classical non-stochastic regret minimization problem with decisions, gains and losses to be respectively maximized or minimized are fundamentally different. Indeed, by considering the additional sparsity assumption (at each stage, at most decisions incur a nonzero outcome), we derive…
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 nonstation…
New adversarial examples with structured distortion sets improve robustness and perceptibility.
Adaptive gradient methods such as AdaGrad and its variants update the stepsize in stochastic gradient descent on the fly according to the gradients received along the way; such methods have gained widespread use in large-scale optimization for their ability to converge robustly, without the need to fine-tune the stepsi…
Unified analysis of FL with arbitrary client participation.
We consider derivative-free algorithms for stochastic and non-stochastic convex optimization problems that use only function values rather than gradients. Focusing on non-asymptotic bounds on convergence rates, we show that if pairs of function values are available, algorithms for -dimensional optimization that use …
A new model for sequential prediction handles adversarial examples by allowing abstention.
New framework for understanding adversarial and stochastic learning.
Paper analyzes adversarial risk using optimal transport.
Modern deep neural network models suffer from adversarial examples, i.e. confidently misclassified points in the input space. It has been shown that Bayesian neural networks are a promising approach for detecting adversarial points, but careful analysis is problematic due to the complexity of these models. Recently Gil…
Study shows adversarial attacks can fool speech-to-text models, and PCA is ineffective as a defense.
Study robustness of split conformal prediction under adversarial attacks.
We present heuristics for solving the maximin problem induced by the generative adversarial privacy setting for linear and convolutional neural network (CNN) adversaries. In the linear adversary setting, we present a greedy algorithm for approximating the optimal solution for the privatizer, which performs better as th…
Study proves existence of robust classifiers in multiclass adversarial training.
This paper examines various definitions of adversarial risk and their implications.
This paper analyzes how machine learning models resist adversarial attacks in nonparametric regression.
The problem of non-stationarity in financial markets is discussed and related to the dynamic nature of price volatility. A new measure is proposed for estimation of the current asset volatility. A simple and illustrative explanation is suggested of the emergence of significant serial autocorrelations in volatility and …
Study efficient learning of robust halfspaces with noise.
We improve adversarial robustness calibration analysis for broader hypothesis sets.
This paper establishes a non-stochastic analogue of the celebrated result by Dubins and Schwarz about reduction of continuous martingales to Brownian motion via time change. We consider an idealized financial security with continuous price path, without making any stochastic assumptions. It is shown that typical price …