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 borrows future randomness to stabilize model-free control.
Reinforcement learning studies how to balance exploration and exploitation in real-world systems, optimizing interactions with the world while simultaneously learning how the world operates. One general class of algorithms for such learning is the multi-armed bandit setting. Randomized probability matching, based upon …
Two new algorithms improve Q* approximation in batch RL with linear error propagation.
We address the problem of multi-class classification in the case where the number of classes is very large. We propose a double sampling strategy on top of a multi-class to binary reduction strategy, which transforms the original multi-class problem into a binary classification problem over pairs of examples. The aim o…
Proposes pT-Learning for optimal dynamic treatment regimes in mHealth.
A real-time federated neural architecture search approach reduces costs and improves performance.
Recently there has been significant interest in training machine-learning models at low precision: by reducing precision, one can reduce computation and communication by one order of magnitude. We examine training at reduced precision, both from a theoretical and practical perspective, and ask: is it possible to train …
We introduce a flexible framework for making inferences about general linear forms of a large matrix based on noisy observations of a subset of its entries. In particular, under mild regularity conditions, we develop a universal procedure to construct asymptotically normal estimators of its linear forms through double-…
New method for causal effect estimation with hidden confounders.
Value function learning plays a central role in many state-of-the-art reinforcement-learning algorithms. Many popular algorithms like Q-learning do not optimize any objective function, but are fixed-point iterations of some variant of Bellman operator that is not necessarily a contraction. As a result, they may easily …
Maximum entropy deep reinforcement learning (RL) methods have been demonstrated on a range of challenging continuous tasks. However, existing methods either suffer from severe instability when training on large off-policy data or cannot scale to tasks with very high state and action dimensionality such as 3D humanoid l…
Paper introduces a new framework to improve sample efficiency in POMDPs learning.
The paper analyzes risk bounds and Rademacher complexity in batch RL.
Study aims to optimize financial investments by balancing risk and reward efficiently.
Off-policy evaluation for MNAR rewards in MDPs
This work investigates the properties of Gaussian-smoothed sliced divergences for comparing distributions.
MGDA converges under generalized smoothness for neural network optimization.