On-device research index

arXiv research

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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “Variance-constrained”

Almost Optimal Variance-Constrained Best Arm Identificationcs.LG

VA-LUCB identifies best arm with variance constraint, achieving optimal sample complexity.

problem Identifying the best arm with variance constraint under fixed confidence.

method Parameter-free algorithm VA-LUCB, analyzing sample complexity and proving lower bounds.

result Optimal sample complexity up to a logarithmic factor in

H_{VA}

, demonstrated by experiments.

Variance-constrained Best arm identification Sample complexity Lower bounds Upper bounds

2022-01-25abs ↗pdf ↗

Variance Constrained Autoencodingcs.LG

VCAE improves autoencoder quality on MNIST and CelebA.

problem Overfitting and poor generative/reconstruction quality in autoencoders.

method Proposes variance-constrained autoencoder (VCAE) to enforce variance constraint on latent distribution.

result VCAE outperforms Wasserstein Autoencoder and Variational Autoencoder in quality.

autoencoder stochastic latent distribution disentanglement total correlation penalty

2020-05-08abs ↗pdf ↗

Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policycs.LG

This work tackles risk-sensitive deep RL by optimizing policies with variance constraints.

problem Risk and aleatoric uncertainty in deep reinforcement learning.

method Lagrangian and Fenchel dualities to transform the problem into an unconstrained saddle-point policy optimization problem, and an actor-critic algorithm to iteratively update policy, Lagrange multiplier, and Fenchel dual variable.

result The proposed actor-critic algorithm finds a globally optimal policy at a sublinear rate.

deep reinforcement learning risk-sensitive policy optimization actor-critic variance constraint

2020-12-28abs ↗pdf ↗

Choquet regularization for reinforcement learningstat.ML

Choquet regularization improves exploration in RL.

problem Improving exploration in reinforcement learning.

method Introducing Choquet regularizers to measure and manage exploration, reformulating RL problems and deriving explicit solutions.

result Explicit optimal distributions and Choquet regularizers for various exploratory samplers.

reinforcement learning exploration entropy regularization Choquet integrals Hamilton-Jacobi-Bellman

2022-08-17abs ↗pdf ↗

Variance-Constrained Actor-Critic Algorithms for Discounted and Average Reward MDPscs.LG

In many sequential decision-making problems we may want to manage risk by minimizing some measure of variability in rewards in addition to maximizing a standard criterion. Variance related risk measures are among the most common risk-sensitive criteria in finance and operations research. However, optimizing many such c…

2014-03-25abs ↗pdf ↗

Dynamic Factor Model-Based Multiperiod Mean-Variance Portfolio Selection with Portfolio Constraintsq-fin.PM

The paper solves multi-period portfolio selection with constraints using a dynamic factor model.

problem Multi-period mean-variance portfolio selection with constraints.

method Dynamic factor model, dynamic programming, piecewise linear feedback policy.

result Optimal portfolio policies determined by two stochastic processes.

portfolio selection dynamic factor model mean-variance constrained optimization dynamic programming

2025-02-25abs ↗pdf ↗

Markov Chain Variance Estimation: A Stochastic Approximation Approachmath.ST

Estimates Markov chain variance efficiently without storing samples.

problem Estimating the asymptotic variance of Markov chain functions.

method Linear stochastic approximation of Poisson equation solution.

result Optimal MSE convergence rate with finite sample guarantees.

Markov chains asymptotic variance stochastic approximation reinforcement learning risk measures

2024-09-09abs ↗pdf ↗