This chapter presents three major reinforcement learning algorithms used for fine-tuning financial forecasters. We propose a clear implementation plan for backpropagating the loss of a reinforcement learning task to a model trained using supervised learning, and compare the performance before and after the fine-tuning. We find an increase in performance after fine-tuning, and transfer learning properties to the models, indicating the benefits of fine-tuning. We also highlight the tuning process and empirical results for future implementation by practitioners.

Ver mais

Classroom When you take a linear algebra course and get to the chapter on eigenvalues, your homework problems will include a small matrix A and you will be asked to find the eigenvalues. You do this by computing the determinant det(A − λI) = P(λ) and getting P(λ), a polynomial in λ. The roots of P are the eigenvalues of A. Either A will be a 2 × 2 matrix, in which case you can find the roots using […]

Ver mais

Class-incremental learning (CIL) is typically evaluated under predefined schedules with equal-sized tasks, leaving more realistic and complex cases unexplored. However, a practical CIL system should learns immediately when any number of new classes arrive, without forcing fixed-size tasks. We formalize this setting as Free-Flow Class-Incremental Learning (FFCIL), where data arrives as a more realistic stream with a highly variable number of unseen classes each step. It will make many existing CIL methods brittle and lead to clear performance […]

Ver mais

This monograph provides a rigorous overview of theoretical and methodological aspects of probabilistic inference and learning with Stein’s method. Recipes are provided for constructing Stein discrepancies from Stein operators and Stein sets, and properties of these discrepancies such as computability, separation, convergence detection, and convergence control are discussed. Further, the connection between Stein operators and Stein variational gradient descent is set out in detail. The main definitions and results are precisely stated, and references to all proofs are […]

Ver mais

This paper studies continuous-time stochastic control problems whose controlled states are fully non-Markovian and depend on unknown model parameters. Such problems arise naturally in path-dependent stochastic differential equations, rough-volatility hedging, and systems driven by fractional Brownian motion. Building on the discrete skeleton approach developed in earlier work, we propose a Monte Carlo learning methodology for the associated embedded backward dynamic programming equation. Our main contribution is twofold. First, we construct explicit dominating training laws and Radon–Nikodym weights for […]

Ver mais

Hi all, I’ve been studying causal inference (mainly through Elias Bareinboim’s lectures) and understand the theoretical side — structural causal models (SCMs), do-calculus, identifiability, backdoor/frontdoor criteria, etc. However, I’m struggling with the implementation side of Causal RL. Most material I’ve found focuses on: – Theorems about identifiability – Action space pruning – Counterfactual reasoning concepts But I’m not finding concrete examples of: How to incorporate a known causal graph into an RL training loop How to parameterize the […]

Ver mais

arXiv:2603.09986v1 Announce Type: new Abstract: Hallucinations, the tendency for large language models to provide responses with factually incorrect and unsupported claims, is a serious problem within natural language processing for which we do not yet have an effective solution to mitigate against. Existing benchmarks for medical QA rarely evaluate this behavior against a fixed evidence source. We ask how often hallucinations occur on textbook-grounded QA and how responses to medical QA prompts vary across models. We conduct two […]

Ver mais