arXiv research

A new GAN loss function based on cumulant generating functions improves stability and robustness.

Optimistic algorithm reduces regret and constraint violations in online convex optimization with adversarial constraints.

New algorithms achieve near-optimal cumulative loss in nonparametric online learning and games.

We consider a financial contract that delivers a single cash flow given by the terminal value of a cumulative gains process. The problem of modelling and pricing such an asset and associated derivatives is important, for example, in the determination of optimal insurance claims reserve policies, and in the pricing of r…

Perceptron is a classic online algorithm for learning a classification function. In this paper, we provide a novel extension of the perceptron algorithm to the learning to rank problem in information retrieval. We consider popular listwise performance measures such as Normalized Discounted Cumulative Gain (NDCG) and Av…

In this paper we provide a valuation formula for different classes of actuarial and financial contracts which depend on a general loss process, by using the Malliavin calculus. In analogy with the celebrated Black-Scholes formula, we aim at expressing the expected cash flow in terms of a building block. The former is r…

This paper extends stock trading results to include stop-loss orders.

New method for neural networks to predict histogram data.

This paper quantifies and mitigates a bias in the Hayashi-Yoshida estimator causing data loss.

A simple formula approximates AUM fees' cumulative costs.

The study optimizes bounds for comparing training and population loss.

Study on sequential prediction with log-loss, focusing on well-specified and misspecified cases.

New framework finds periodic policies in reset-free MDPs with sublinear regret.

Adapts Exp3 to adversarial bandits with delays and data.

Optimal exit strategies of CPT gamblers in unfair gambles

Constructs classifiers for neural networks with specific data configurations.

New algorithm minimizes cumulative loss in dynamic linear bandits without prior knowledge of comparator switches.

Selective reinitialization improves adaptability of neural bandits in dynamic environments.

Develops uniform convergence guarantees for a broad class of risk functionals in supervised learning.

This paper proposes a new methodology to compute Value at Risk (VaR) for quantifying losses in credit portfolios. We approximate the cumulative distribution of the loss function by a finite combination of Haar wavelets basis functions and calculate the coefficients of the approximation by inverting its Laplace transfor…

Reduces dynamic regret to static problem in RKHS.

We present an adaptive online gradient descent algorithm to solve online convex optimization problems with long-term constraints , which are constraints that need to be satisfied when accumulated over a finite number of rounds T , but can be violated in intermediate rounds. For some user-defined trade-off parameter $β$…

In this work we consider adversarial contextual bandits with risk constraints. At each round, nature prepares a context, a cost for each arm, and additionally a risk for each arm. The learner leverages the context to pull an arm and then receives the corresponding cost and risk associated with the pulled arm. In additi…

Estimates MLP expected output without sampling, using fewer FLOPs.

Improved regret bounds for adversarial linear contextual bandits.

Exponential dispersion model is a useful framework in machine learning and statistics. Primarily, thanks to the additive structure of the model, it can be achieved without difficulty to estimate parameters including mean. However, tight conditions on cumulant function, such as analyticity, strict convexity, and steepne…

Paper introduces a new $G^\star$ regret measure for online convex optimization with smooth losses.

New algorithm reduces constraint violation to $O(T^{1/3})$ while maintaining $O(\sqrt{T})$ regret.

Develops a model for gambling decisions under time inconsistency.

We analyze the semi-hard triplet loss using Edgeworth expansion for better understanding of its behavior.

New algorithms reduce dynamic regret for convex and smooth functions in non-stationary environments.

New algorithms minimize regret in both adversarial and stochastic contexts.

We consider an arbitrage-free, discrete time and frictionless market. We prove that an investor maximising the expected utility of her terminal wealth can always find an optimal investment strategy provided that her dissatisfaction of infinite losses is infinite and her utility function is non-decreasing, continuous an…

The goal of a learner, in standard online learning, is to have the cumulative loss not much larger compared with the best-performing function from some fixed class. Numerous algorithms were shown to have this gap arbitrarily close to zero, compared with the best function that is chosen off-line. Nevertheless, many real…

Continuous-time Kyle model shows privacy subsidy from noise-perturbed order flow.

Improved cumulative regret for sequence prediction with limited expert advice.

We consider the problem of bandit optimization, inspired by stochastic optimization and online learning problems with bandit feedback. In this problem, the objective is to minimize a global loss function of all the actions, not necessarily a cumulative loss. This framework allows us to study a very general class of pro…

LinConTS improves regret and constraint violations in probabilistic linearly constrained bandits.

The paper tackles multi-armed bandits with vector losses, focusing on minimizing the $\ell^\infty$-norm of relative losses.

DE-QT detects optimal Q-learning stopping points.

Paper improves PAC-Bayes bounds for various loss types.

MaxCOSD algorithm tackles non-i.i.d. demands and stateful dynamics in online inventory control.

In this paper we study a spectrally negative Lévy process which is refracted at its running maximum and at the same time reflected from below at a certain level. Such a process can for instance be used to model an insurance surplus process subject to tax payments according to a loss-carry-forward scheme together with t…

Study quantifies how LLMs capture higher-order statistical structure using cumulant expansion.

We introduce novel variants of momentum by incorporating the variance of the stochastic loss function. The variance characterizes the confidence or uncertainty of the local features of the averaged loss surface across the i.i.d. subsets of the training data defined by the mini-batches. We show two applications of the g…

The CSA-ES is an Evolution Strategy with Cumulative Step size Adaptation, where the step size is adapted measuring the length of a so-called cumulative path. The cumulative path is a combination of the previous steps realized by the algorithm, where the importance of each step decreases with time. This article studies …

Optimal algorithms for online convex optimization with random order.

Improved COCO algorithms with better constraint control.