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.
This work tackles representation learning by introducing stochastic competition-based activations.
Study competitive energy markets using stochastic impulse games.
Two-layer model studies reinsurance contracts and competition between insurer and reinsurers.
Investigates portfolio selection among competitive agents with mean-variance preferences.
Improves bandits with knapsacks guarantees for partially stochastic workloads.
Paper studies competitive networks where teams aim to minimize their own objectives, adapting to each other's strategies.
New model considers unfairness complaints to ensure multiple fairness criteria.
We present examples of agent-based and stochastic models of competition and business processes in economics and finance. We start from as simple as possible models, which have microscopic, agent-based, versions and macroscopic treatment in behavior. Microscopic and macroscopic versions of herding model proposed by Kirm…
Algorithm for decentralized competition among adaptive agents.
We develop the method of stochastic modified equations (SME), in which stochastic gradient algorithms are approximated in the weak sense by continuous-time stochastic differential equations. We exploit the continuous formulation together with optimal control theory to derive novel adaptive hyper-parameter adjustment po…
Study examines strategic exit timing in uncertain competition.
The paper extends macroscopic market making to stochastic games, revealing properties and solving equations.
Study optimal investment in large populations of competitive, heterogeneous agents.
Investors' strategic trading affects asset prices, modeled as a game.
Bipartite ranking is an important supervised learning problem; however, unlike regression or classification, it has a quadratic dependence on the number of samples. To circumvent the prohibitive sample cost, many recent work focus on stochastic gradient-based methods. In this paper we consider an alternative approach, …
Adaptive volatility method improves probabilistic financial forecasting.
We introduce algorithms for online, full-information prediction that are competitive with contextual tree experts of unknown complexity, in both probabilistic and adversarial settings. We show that by incorporating a probabilistic framework of structural risk minimization into existing adaptive algorithms, we can robus…
Finding parameters that minimise a loss function is at the core of many machine learning methods. The Stochastic Gradient Descent algorithm is widely used and delivers state of the art results for many problems. Nonetheless, Stochastic Gradient Descent typically cannot find the global minimum, thus its empirical effect…
The paper analyzes reinsurance strategies in a competitive multi-agent system.
The adjoint sensitivity method scalably computes gradients of solutions to ordinary differential equations. We generalize this method to stochastic differential equations, allowing time-efficient and constant-memory computation of gradients with high-order adaptive solvers. Specifically, we derive a stochastic differen…
We consider a class of discrete time stochastic control problems motivated by some financial applications. We use a pathwise stochastic control approach to provide a dual formulation of the problem. This enables us to develop a numerical technique for obtaining an estimate of the value function which improves on purely…
Study of insurer games with model uncertainty in reinsurance and investment strategies.
New SPS variant improves non-smooth optimization without small gradients.
Motivated by applications in recommender systems, web search, social choice and crowdsourcing, we consider the problem of identifying the set of top items from noisy pairwise comparisons. In our setting, we are non-actively given pairwise comparisons between each pair of items, where each comparison has noi…
Many machine learning algorithms minimize a regularized risk, and stochastic optimization is widely used for this task. When working with massive data, it is desirable to perform stochastic optimization in parallel. Unfortunately, many existing stochastic optimization algorithms cannot be parallelized efficiently. In t…
Model predicts BESS interactions and price impacts in energy markets.
We study optimal behavior of energy producers under a CO_2 emission abatement program. We focus on a two-player discrete-time model where each producer is sequentially optimizing her emission and production schedules. The game-theoretic aspect is captured through a reduced-form price-impact model for the CO_2 allowance…
Adaptive learning rate improves FTRL's performance in online learning.
Greedy algorithm performs well in online matching despite non-i.i.d. connections.
We develop a scalable method for Bayesian neural networks with stochastic differential equations.
Study -player and mean-field games in Itô-diffusion markets with competitive or homophilous interactions.
A method for large scale Gaussian process classification has been recently proposed based on expectation propagation (EP). Such a method allows Gaussian process classifiers to be trained on very large datasets that were out of the reach of previous deployments of EP and has been shown to be competitive with related tec…
Study cooperative bandit learning with imperfect communication, achieving near-optimal performance.
Study optimal reinsurance strategies in a game between insurer and two reinsurers.
This paper studies the performance of a recently proposed preconditioned stochastic gradient descent (PSGD) algorithm on recurrent neural network (RNN) training. PSGD adaptively estimates a preconditioner to accelerate gradient descent, and is designed to be simple, general and easy to use, as stochastic gradient desce…
Stochastic LWTA networks resist adversarial attacks while maintaining accuracy.
We consider Bandits with Knapsacks (henceforth, BwK), a general model for multi-armed bandits under supply/budget constraints. In particular, a bandit algorithm needs to solve a well-known knapsack problem: find an optimal packing of items into a limited-size knapsack. The BwK problem is a common generalization of nume…
Hessian-free (HF) optimization has been successfully used for training deep autoencoders and recurrent networks. HF uses the conjugate gradient algorithm to construct update directions through curvature-vector products that can be computed on the same order of time as gradients. In this paper we exploit this property a…
The study examines how alternative resource adequacy contract designs affect market participants' risk profiles and resource mix.
Most sales applications are characterized by competition and limited demand information. For successful pricing strategies, frequent price adjustments as well as anticipation of market dynamics are crucial. Both effects are challenging as competitive markets are complex and computations of optimized pricing adjustments…
Develops DP-SCD for stochastic coordinate descent, making it differentially private.
Convolutional architectures have recently been shown to be competitive on many sequence modelling tasks when compared to the de-facto standard of recurrent neural networks (RNNs), while providing computational and modeling advantages due to inherent parallelism. However, currently there remains a performance gap to mor…
Model-free learning for multi-agent stochastic games is an active area of research. Existing reinforcement learning algorithms, however, are often restricted to zero-sum games, and are applicable only in small state-action spaces or other simplified settings. Here, we develop a new data efficient Deep-Q-learning method…
Recent advances in variational inference enable the modelling of highly structured joint distributions, but are limited in their capacity to scale to the high-dimensional setting of stochastic neural networks. This limitation motivates a need for scalable parameterizations of the noise generation process, in a manner t…
Stochastic gradient descent is the method of choice for large-scale machine learning problems, by virtue of its light complexity per iteration. However, it lags behind its non-stochastic counterparts with respect to the convergence rate, due to high variance introduced by the stochastic updates. The popular Stochastic …
This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employed for typical functional tasks such as regression and classification. We optimize hypernetworks to directly maximize the conditional likelih…
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…
New method improves training stochastic neural networks with tighter guarantees.