arXiv research

Improved prediction algorithm for 'easy' sequences with reduced regret.

New RL algorithm tackles adversarial RMAB with unknown transitions and bandit feedback.

SMEs provide a transparent testbed for RL evaluation.

TVBO optimizes time-varying functions with asymptotically vanishing regret.

This paper analyzes local optimizers in Bayesian optimization for expensive functions.

This paper introduces a new metric, ULI, for RL that ensures both cumulative and instantaneous performance.

New algorithm tackles multi-armed bandits with abstention, achieving optimal regret bounds.

New algorithm reduces regret in stochastic shortest path problems.

We consider a collaborative online learning paradigm, wherein a group of agents connected through a social network are engaged in playing a stochastic multi-armed bandit game. Each time an agent takes an action, the corresponding reward is instantaneously observed by the agent, as well as its neighbours in the social n…

We study online aggregation of the predictions of experts, and first show new second-order regret bounds in the standard setting, which are obtained via a version of the Prod algorithm (and also a version of the polynomially weighted average algorithm) with multiple learning rates. These bounds are in terms of excess l…

New MAB model for online caching costs.

We address the online linear optimization problem with bandit feedback. Our contribution is twofold. First, we provide an algorithm (based on exponential weights) with a regret of order $\sqrt{d n \log N}$ for any finite action set with $N$ actions, under the assumption that the instantaneous loss is bounded by 1. This…

New geometric metrics improve Bayesian optimization performance evaluation.

Two new algorithms optimize rewards while respecting safety constraints in sequential decisions.

Study cooperative bandit learning with imperfect communication, achieving near-optimal performance.

We prove uniqueness of instantaneously complete Ricci flows on surfaces. We do not require any bounds of any form on the curvature or its growth at infinity, nor on the metric or its growth (other than that implied by instantaneous completeness). Coupled with earlier work, particularly [23, 11], this completes the well…

Paper explores arbitrage and CAPM in continuous time.

New framework IDOL identifies latent causal processes with instantaneous relations from time series data.

New formula for instantaneous frequency in unbalanced systems.

Study minimax rates for online learning with time-varying dynamics.

iCITRIS learns causal variables from interactive systems with instantaneous effects.

We consider a system where agents enter in an online fashion and are evaluated based on their attributes or context vectors. There can be practical situations where this context is partially observed, and the unobserved part comes after some delay. We assume that an agent, once left, cannot re-enter the system. Therefo…

Study compares Fourier estimators to mitigate asynchrony effects in finance.

Existing approaches to online convex optimization (OCO) make sequential one-slot-ahead decisions, which lead to (possibly adversarial) losses that drive subsequent decision iterates. Their performance is evaluated by the so-called regret that measures the difference of losses between the online solution and the best ye…

Online algorithms for identifying river pollution sources.

The Ricci flow preserves product structures with instantaneous curvature bounds.

This work improves wireless network learning by using side-information about interference.

Noiseless IO bounds inferred from demonstrations, matching adversarial settings.

Paper revises power theory using classical mechanics concepts.

Instantaneous volatility estimated from traded volume and spread.

New algorithm resists corruption in linear contextual bandits.

Study cryptocurrency price dynamics using adaptive EMD and spectral analysis.

Modeling continuous movement of entities in latent space for interaction timing.

We study hedging and pricing of unattainable contingent claims in a non-Markovian regime-switching financial model. Our financial market consists of a bank account and a risky asset whose dynamics are driven by a Brownian motion and a multivariate counting process with stochastic intensities. The interest rate, drift, …

A new stochastic volatility model with quadratic drift prevents moment explosions and preserves stock price martingale property.

Study on Yamabe flow on manifolds with singularities, proving removability.

Collective behaviours taking place in financial markets reveal strongly correlated states especially during a crisis period. A natural hypothesis is that trend reversals are also driven by mutual influences between the different stock exchanges. Using a maximum entropy approach, we find coordinated behaviour during tre…

Global existence of Yamabe flows on hyperbolic space proved without curvature bounds.

Study optimal execution in a transient price impact model with multiple traders.

Estimates chirp signal frequencies using probabilistic models.

A new principle minimizes residual and introduces momentum to improve PDE solution dynamics.

New model identifies regimes in non-stationary data.

Unified framework for optimal liquidation with small market impact and semimartingale strategies.

To convert standard Brownian motion $Z$ into a positive process, Geometric Brownian motion (GBM) $e^{βZ_t}, β>0$ is widely used. We generalize this positive process by introducing an asymmetry parameter $α\geq 0$ which describes the instantaneous volatility whenever the process reaches a new low. For our new process, …

An average instantaneous cross-correlation function is introduced to quantify the interaction of the financial market of a specific time. Based on the daily data of the American and Chinese stock markets, memory effect of the average instantaneous cross-correlations is investigated over different price return time inte…

Paper revisits five IF paradoxes using differential geometry.

We develop a theory for valuing non-diversifiable mortality risk in an incomplete market. We do this by assuming that the company issuing a mortality-contingent claim requires compensation for this risk in the form of a pre-specified instantaneous Sharpe ratio. We apply our method to value life annuities. One result of…

We use a continuous version of the standard deviation premium principle for pricing in incomplete equity markets by assuming that the investor issuing an unhedgeable derivative security requires compensation for this risk in the form of a pre-specified instantaneous Sharpe ratio. First, we apply our method to price opt…