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 algorithm tackles delayed feedback in Lipschitz bandits with sublinear regret.
New algorithm tackles stochastic bandits with varying arm-dependent delays.
Develops a stochastic approach to financial market delays.
New method solves stochastic control problems with delays using deep learning.
We provide tight finite-time convergence bounds for gradient descent and stochastic gradient descent on quadratic functions, when the gradients are delayed and reflect iterates from rounds ago. First, we show that without stochastic noise, delays strongly affect the attainable optimization error: In fact, the error…
DASA speeds up SA with delayed agents, achieving N-fold speedup.
Deep neural networks solve stochastic control problems with delay.
We study a variant of the stochastic -armed bandit problem, which we call "bandits with delayed, aggregated anonymous feedback". In this problem, when the player pulls an arm, a reward is generated, however it is not immediately observed. Instead, at the end of each round the player observes only the sum of a number…
The paper solves optimal control problems for stochastic delay equations.
Improved algorithm for bandits with delayed feedback, combining adversarial and stochastic performance.
We analyze the convergence of gradient-based optimization algorithms that base their updates on delayed stochastic gradient information. The main application of our results is to the development of gradient-based distributed optimization algorithms where a master node performs parameter updates while worker nodes compu…
This paper presents a stochastic logic time delay reservoir design. The reservoir is analyzed using a number of metrics, such as kernel quality, generalization rank, performance on simple benchmarks, and is also compared to a deterministic design. A novel re-seeding method is introduced to reduce the adverse effects of…
Delay-SDE-net models time series with memory and uncertainty, outperforming other models.
Stochastic linear bandits are a natural and well-studied model for structured exploration/exploitation problems and are widely used in applications such as online marketing and recommendation. One of the main challenges faced by practitioners hoping to apply existing algorithms is that usually the feedback is randomly …
We study distributed stochastic convex optimization under the delayed gradient model where the server nodes perform parameter updates, while the worker nodes compute stochastic gradients. We discuss, analyze, and experiment with a setup motivated by the behavior of real-world distributed computation networks, where the…
Enhances SGLD for log-concave posteriors with asynchronous computation.
Study proves convergence of interest rate model approximations.
New algorithm reduces distributed optimization time with stochastic delays.
We analyze (stochastic) gradient descent (SGD) with delayed updates on smooth quasi-convex and non-convex functions and derive concise, non-asymptotic, convergence rates. We show that the rate of convergence in all cases consists of two terms: (i) a stochastic term which is not affected by the delay, and (ii) a higher …
Paper develops Euler scheme for fractional delay diff. eqs with additive noise.
We consider that the price of a firm follows a non linear stochastic delay differential equation. We also assume that any claim value whose value depends on firm value and time follows a non linear stochastic delay differential equation. Using self-financed strategy and replication we are able to derive a Random Partia…
Optimal trading strategy between CEXs and DEXs with priority fees and stochastic delays.
Understanding the convergence performance of asynchronous stochastic gradient descent method (Async-SGD) has received increasing attention in recent years due to their foundational role in machine learning. To date, however, most of the existing works are restricted to either bounded gradient delays or convex settings.…
Proposes a deep learning method for solving complex financial games with delays.
This article is a sequel to [A.H.M.P]. In [A.H.M.P], we develop an explicit formula for pricing European options when the underlying stock price follows a non-linear stochastic delay equation with fixed delays in the drift and diffusion terms. In this article, we look at models of the stock price described by stochasti…
Paper tackles dueling bandits with delayed feedback, revealing preference bias.
The paper models financial asset prices with jumps and evaluates European option prices using numerical methods.
We propose a model of inter-bank lending and borrowing which takes into account clearing debt obligations. The evolution of log-monetary reserves of banks is described by coupled diffusions driven by controls with delay in their drifts. Banks are minimizing their finite-horizon objective functions which take into a…
In this article we propose a model for stochastic delay differential equation with jumps (SDDEJ) in a differentiable manifold endowed with a connection . In our model, the continuous part is driven by vector fields with a fixed delay and the jumps are assumed to come from a distinct source of (càdlàg) noise…
Novel algorithm for decentralized optimization in time-varying networks with delays.
New algorithm reduces regret in delayed feedback generalised linear bandits.
Online learning with delayed feedback has received increasing attention recently due to its several applications in distributed, web-based learning problems. In this paper we provide a systematic study of the topic, and analyze the effect of delay on the regret of online learning algorithms. Somewhat surprisingly, it t…
New algorithms ensure fair selection in combinatorial semi-bandit with unrestricted delays.
In this paper we investigate novel applications of a new class of equations which we call time-delayed backward stochastic differential equations. Time-delayed BSDEs may arise in finance when we want to find an investment strategy and an investment portfolio which should replicate a liability or meet a target depending…
Stochastic delay differential equations (SDDE's) have been used for financial modeling. In this article, we study a SDDE obtained by the equation of a CIR process, with an additional fixed delay term in drift; in particular, we prove that there exists a unique strong solution (positive and integrable) which we call fix…
New algorithm tackles non-stationary delayed feedback in recommender systems.
Study optimal portfolios for traders with asymmetric information and delay.
Adapts two algorithms for online learning with delayed rewards.
This paper investigates a hybrid stochastic differential reinsurance and investment game between one reinsurer and two insurers, including a stochastic Stackelberg differential subgame and a non-zero-sum stochastic differential subgame. The reinsurer, as the leader of the Stackelberg game, can price reinsurance premium…
Develops a new bivariate process for energy markets with improved simulation methods.
Study cooperative bandit learning with imperfect communication, achieving near-optimal performance.
New method speeds up training of large kernel models.
This study analyzes satellite communication latency using a stochastic geometry model.
Study utility maximization with delayed information in continuous time Gaussian markets.
We propose an optimal portfolio problem in the incomplete market where the underlying assets depend on economic factors with delayed effects, such models can describe the short term forecasting and the interaction with time lag among different financial markets. The delay phenomenon can be recognized as the integral ty…
New algorithm optimizes noisy function evaluations with delayed feedback.
We explore a novel setting of the Multi-Armed Bandit (MAB) problem inspired from real world applications which we call bandits with "stochastic delayed composite anonymous feedback (SDCAF)". In SDCAF, the rewards on pulling arms are stochastic with respect to time but spread over a fixed number of time steps in the fut…
New RL algorithm handles delayed feedback with posterior sampling.