arXiv research

Paper solves no-swap regret minimization for combinatorial bandits with polylogarithmic dependence on N.

Improved online algorithm for convex losses with near-optimal swap regret.

The paper improves on existing algorithms for minimizing different types of regret in online learning.

New algorithm calibrates forecasts in high dimensions with minimal regret.

Algorithm minimizes regret and converges to equilibria in Markov games.

Paper tackles hidden game problem in AI alignment and language games.

New algorithm achieves online calibration in polynomial time for high-dimensional problems.

New calibration measure SCDL improves trust in AI predictions.

New insights link no-regret learning to online conformal prediction in adversarial settings.

We introduce CSE for MLSF games and devise online learning algorithms for achieving no-external Stackelberg-regret.

This paper investigates the pricing and hedging of variance swaps under a $3/2$ volatility model. Explicit pricing and hedging formulas of variance swaps are obtained under the benchmark approach, which only requires the existence of the numéraire portfolio. The growth optimal portfolio is the numéraire portfolio and u…

Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the standard definition of regret becomes inadequate if the adversary is allowed to a…

Swapping debt contracts can mitigate risk in financial networks.

Improved bounds for multicalibration and omniprediction in online and distributional settings.

In recent years, constrained optimization has become increasingly relevant to the machine learning community, with applications including Neyman-Pearson classification, robust optimization, and fair machine learning. A natural approach to constrained optimization is to optimize the Lagrangian, but this is not guarantee…

DDLK uses deep learning to find important features in models.

New algorithm for online omniprediction with strong guarantees for continuous hypothesis classes.

This paper demonstrates a practical method for computing the solution of an expectation-constrained robust maximization problem with immediate applications to model-free no-arbitrage bounds and super-replication values for many financial derivatives. While the previous literature has connected super-replication values …

Regret minimization is treated as the golden rule in the traditional study of online learning. However, regret minimization algorithms tend to converge to the static optimum, thus being suboptimal for changing environments. To address this limitation, new performance measures, including dynamic regret and adaptive regr…

Regret minimization is a powerful tool for solving large-scale problems; it was recently used in breakthrough results for large-scale extensive-form game solving. This was achieved by composing simplex regret minimizers into an overall regret-minimization framework for extensive-form game strategy spaces. In this paper…

This paper presents hedging strategies for European and exotic options in a Levy market. By applying Taylor's Theorem, dynamic hedging portfolios are con- structed under different market assumptions, such as the existence of power jump assets or moment swaps. In the case of European options or baskets of European optio…

Debt swaps improve financial networks by optimizing clearing payments and stability.

The paper introduces a new stochastic volatility model with long-term memory and jumps.

New learning dynamics adapt to corrupted games, improving performance in real-world scenarios.

We consider regret minimization in repeated games with non-convex loss functions. Minimizing the standard notion of regret is computationally intractable. Thus, we define a natural notion of regret which permits efficient optimization and generalizes offline guarantees for convergence to an approximate local optimum. W…

The paper tackles best arm identification with minimal regret in experiments.

New algorithms minimize simple and cumulative regret in contextual bandits.

In this paper the zero vanna implied volatility approximation for the price of freshly minted volatility swaps is generalised to seasoned volatility swaps. We also derive how volatility swaps can be hedged using a strip of vanilla options with weights that are directly related to trading intuition. Additionally, we der…

We derive an arbitrage free relationship between recovery swap rates, digital default swap spreads and conventional CDS spreads, and argue that the fair forward recovery rate used in recovery swaps must contain a convexity premium over the expected recovery value.

There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are a sub-class of MABs where, at every time step, the learner has access to side in…

GPU (graphics processing unit) has been used for many data-intensive applications. Among them, deep learning systems are one of the most important consumer systems for GPU nowadays. As deep learning applications impose deeper and larger models in order to achieve higher accuracy, memory management becomes an important …

New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.

The paper prices swaps on generalized variance measures for multiple assets.

The paper minimizes Borda regret in dueling bandits models.

This paper begins with a study on the dual representations of risk and regret measures and their impact on modeling multistage decision making under uncertainty. A relationship between risk envelopes and regret envelopes is established by using the Lagrangian duality theory. Such a relationship opens a door to a decomp…

New algorithm optimizes DAGs by swapping node pairs to avoid cycles.

This study reviews techniques to estimate volatility and price Variance Swaps.

Paper explores rate-preserving reductions between Blackwell approachability and no-regret learning.

F. Labourie [arXiv:1212.5015] characterized the Hitchin components for $\operatorname{PSL}(n, \mathbb{R})$ for any $n>1$ by using the swapping algebra, where the swapping algebra should be understood as a ring equipped with a Poisson bracket. We introduce the rank $n$ swapping algebra, which is the quotient of the swap…

New online conformal prediction methods minimize strongly adaptive regret and achieve near-optimal coverage.

In this paper, we model financial markets with semi-Markov volatilities and price covarinace and correlation swaps for this markets. Numerical evaluations of vari- nace, volatility, covarinace and correlations swaps with semi-Markov volatility are presented as well. The novelty of the paper lies in pricing of volatilit…

Exact relationships found between ATM slope, volatility swap, and zero vanna.

An uncollateralized swap hedged back-to-back by a CCP swap is used to introduce FVA. The open IR01 of FVA, however, is a sure sign of risk not being fully hedged, a theoretical no-arbitrage pricing concern, and a bait to lure market risk capital, a practical business concern. By dynamically trading the CCP swap, with t…

A note on setting swap parameters for traders.

New algorithm minimizes Bayesian regret in offline linear bandits.

Dynamic regret minimization is shown equivalent to static regret minimization for linear losses.

New algorithm reduces regret by allowing free exploration in multi-armed bandits.

Protocol learns pure quantum states with minimal disturbance.