arXiv research

New model values equity-linked securities with guaranteed return.

Embedding RL policies in RKHS for robustness and theoretical guarantees.

Deep reinforcement learning improves trading performance with predictable returns.

Exponential functionals of Brownian motion have been extensively studied in financial and insurance mathematics due to their broad applications, for example, in the pricing of Asian options. The Black-Scholes model is appealing because of mathematical tractability, yet empirical evidence shows that geometric Brownian m…

Model approximates market prices and returns without prior market dynamics.

New algorithms improve performance guarantees for multi-armed bandits problems.

This paper applies quantum probability theory to model asset returns, avoiding assumptions about quantum effects.

Estimates mean and covariance for large, unbalanced stock returns panels.

We consider a discrete-time, linear state equation with delay which arises as a model for a trader's account value when buying and selling a risky asset in a financial market. The state equation includes a nonnegative feedback gain $α$ and a sequence $v(k)$ which models asset returns which are within known bounds but o…

Growth-optimal portfolios are guaranteed to accumulate higher wealth than any other investment strategy in the long run. However, they tend to be risky in the short term. For serially uncorrelated markets, similar portfolios with more robust guarantees have been recently proposed. This paper extends these robust portfo…

This work provides guarantees for off-policy function estimation under realizability assumptions.

NFTs with diverse rare attributes sell at higher prices.

T-SCI improves Cox-MLP's guaranteed coverage for censored data.

A model explains stock returns and volatility using multifractal and rough components.

Unified framework for reliable uncertainty quantification in RL.

New pension design reduces volatility without guarantees.

PS^2 selects assets then weights for high-dimensional investing.

Diminishing-returns (DR) submodular optimization is an important field with many real-world applications in machine learning, economics and communication systems. It captures a subclass of non-convex optimization that provides both practical and theoretical guarantees. In this paper, we study the fundamental problem of…

Constructs tail-specific prediction intervals for financial applications

Variable annuities (VA) are popular insurance products. VAs provides the insured with a guaranteed accumulation rate on their premium at maturity. In addition, the insured may receive extra benefit if returns of underlying funds are high enough. Here we consider a special case of VA with high-water mark feature and Gua…

Algorithm learns decision trees from noisy data.

New algorithm for online portfolio selection with reduced runtime.

New method tackles online DR-submodular maximization with improved regret guarantees.

Develops a unified framework for valuing insurance products with guarantees.

The guaranteed minimum withdrawal benefit (GMWB) rider, as an add on to a variable annuity (VA), guarantees the return of premiums in the form of peri- odic withdrawals while allowing policyholders to participate fully in any market gains. GMWB riders represent an embedded option on the account value with a fee structu…

CDS (credit default swap) contracts that were initiated some time ago frequently have spreads and/or maturities that are not available on the current market of CDSs, and are thus illiquid. This article introduces an incomplete-market approach to valuing illiquid CDSs that, in contrast to the risk-neutral approach of cu…

We study the problem of maximizing a monotone set function subject to a cardinality constraint $k$ in the setting where some number of elements $τ$ is deleted from the returned set. The focus of this work is on the worst-case adversarial setting. While there exist constant-factor guarantees when the function is submodu…

We design a non-convex second-order optimization algorithm that is guaranteed to return an approximate local minimum in time which scales linearly in the underlying dimension and the number of training examples. The time complexity of our algorithm to find an approximate local minimum is even faster than that of gradie…

Understanding generalization in reinforcement learning (RL) is a significant challenge, as many common assumptions of traditional supervised learning theory do not apply. We focus on the special class of reparameterizable RL problems, where the trajectory distribution can be decomposed using the reparametrization trick…

A variable annuity is an equity-linked financial product typically offered by insurance companies. The policyholder makes an upfront payment to the insurance company and, in return, the insurer is required to make a series of payments starting at an agreed upon date. For a higher premium, many insurance companies offer…

Multi-armed bandits are a quintessential machine learning problem requiring the balancing of exploration and exploitation. While there has been progress in developing algorithms with strong theoretical guarantees, there has been less focus on practical near-optimal finite-time performance. In this paper, we propose an …

Ridge leverage scores provide a balance between low-rank approximation and regularization, and are ubiquitous in randomized linear algebra and machine learning. Deterministic algorithms are also of interest in the moderately big data regime, because deterministic algorithms provide interpretability to the practitioner …

Optimizes bidding strategies for LinkedIn ads across multiple platforms.

New algorithm offers costless model selection in contextual bandits.

MDS selects assets by combining daily returns and intraday risk curves, improving portfolio performance.

p-index approach shows efficient-contrarian strategy outperforms others in low-sentiment periods

We address the problem of computing reliable policies in reinforcement learning problems with limited data. In particular, we compute policies that achieve good returns with high confidence when deployed. This objective, known as the \emph{percentile criterion}, can be optimized using Robust MDPs~(RMDPs). RMDPs general…

In this paper the multivariate fractional trading ansatz of money management from Ralph Vince (Portfolio Management Formulas: Mathematical Trading Methods for the Futures, Options, and Stock Markets, John Wiley & Sons, Inc., 1990) is discussed. In particular, we prove existence and uniqueness of an optimal f of the res…

Guaranteed bounds for posterior inference in probabilistic programs.

We study the problem of maximizing a monotone submodular function subject to a cardinality constraint $k$, with the added twist that a number of items $τ$ from the returned set may be removed. We focus on the worst-case setting considered in (Orlin et al., 2016), in which a constant-factor approximation guarantee was g…

Proposes a model to generate high-dimensional financial returns using latent factor structure.

The paper improves recommendation systems by ensuring their outputs are reliable.

Gradient-free ensemble learns sector forecasts from diverse models.

Paper develops a new estimator for MDPs' risk functionals with lower variance and bias.

A key problem in reinforcement learning for control with general function approximators (such as deep neural networks and other nonlinear functions) is that, for many algorithms employed in practice, updates to the policy or $Q$-function may fail to improve performance---or worse, actually cause the policy performance …

Investors can achieve optimal risk-reward trade-offs with bonds and stocks under mean-reverting stock returns.

Optimizes retirement income with MBGs and neural networks for longevity risk.

Paper proposes a new risk measure (reward volatility) for optimizing financial decisions.