arXiv subjects

Miquel Noguer I Alonso

Publications and source records attributed to Miquel Noguer I Alonso.

3 recordsLinked to original sources

arXiv2026

Tail Risk Management with Puts and Trend Following: A CVaR Framework for Crashes and Drawdowns

Tail-risk management is not only an instrument-selection problem. It is an allocation problem across loss mechanisms: abrupt crash states, volatility repricing, and persistent drawdowns require different forms of protection. This paper develops a continuous-time CVaR framework that places two common protection sleeves -- long out-of-the-money put options and systematic trend-following overlays -- inside one coherent tail-risk mandate. The option sleeve is modeled as a marked-to-market traded asset, so premium drag, diffusion exposure, and jump repricing enter through its physical return process rather than through inconsistent terminal-payoff accounting. The resulting Markov state contains wealth, spot, stochastic variance, and an exponentially weighted log-return signal, and we derive the associated Hamilton--Jacobi--Bellman equation in viscosity form. The main analytical separation is temporal: convex insurance reprices immediately on jump impact, whereas trend following is late on the first shock because its signal must cross zero, but becomes increasingly defensive during persistent drawdowns without requiring fresh option premium. We then give sufficient and local conditions for an interior hybrid allocation, derive a CVaR policy-gradient identity, and introduce a four-axis diagnostic layer separating conditional convexity, tail-event reliability, non-stress carry, and drawdown persistence. Stylized Monte Carlo experiments illustrate the mechanism: fixed equal-weight hybrids and grid-optimized hybrids reduce terminal CVaR relative to either pure sleeve in the reported regimes, while the exact weight location remains calibration-dependent. The contribution is a transparent risk-management framework for deciding how much convex crash protection and how much signal-driven drawdown protection a mandate should hold.

q-fin.MF↗

arXiv2026

Pretrained Time-Series Foundation Models for Financial Return Forecasting

Financial return forecasting is a difficult test case for time-series foundation models (TSFMs) due to low signal-to-noise ratios, structural breaks, heavy tails, and weak persistence. This paper benchmarks pretrained TSFMs against train-from-scratch neural baselines in a deliberately conservative financial setting. We evaluate TimeGPT/TimeGPT-LH, TimesFM-2.5, Moirai-2.0, Chronos, and Chronos-2 against NBEATS, NHITS, PatchTST, iTransformer, and KAN on five liquid U.S. equities (AAPL, AMZN, GOOG, JPM, META) using linear and log returns. Models are compared under an equalized context budget, a rolling-origin protocol, and against random-walk benchmarks. We provide a theoretical framing of pretraining as an inductive prior, linking PAC-Bayes transfer intuition, information-theoretic predictability limits, and attention geometry. This clarifies why strong model rankings need not imply economically meaningful predictability in noisy markets. Pragmatically, pretrained TSFMs dominate the ranking distribution, accounting for 8 of 10 task-level wins. Moirai-2.0 and TimesFM-2.5 achieve the strongest average ranks, leading tasks for AAPL, JPM, GOOG, and AMZN, while Chronos wins the remaining AMZN task. However, the iTransformer baseline wins both META tasks, showing local supervised learning can still outperform generic pretraining for specific assets. Crucially, gains over the random-walk benchmark are small and sparse. A one-sided Diebold-Mariano test rejects equal or inferior predictive accuracy only for Chronos on AMZN and Moirai-2.0 on GOOG. We conclude that TSFMs serve as useful practical priors that reduce model-development costs in low-data financial forecasting, but are not universal engines for statistically reliable alpha generation in realistic empirical deployment.

q-fin.MF↗

arXiv2026

Derivative-Informed Operator Learning for Finance: On-the-Fly Greeks, Surfaces, Hedging, and Control

Financial decision systems require fast surrogate models for pricing, calibration, hedging, XVA, stress testing, and portfolio optimization. Standard neural surrogates reproduce prices or risk quantities, but downstream tasks depend as much on derivatives: deltas, vegas, curve and credit-spread sensitivities, exposure and objective gradients. We formulate a derivative-informed operator-learning framework in which the learned map -- a neural operator, random-feature operator, or finite-dimensional surrogate -- is trained both to match a high-fidelity pricing or risk operator and to match directional Fréchet derivatives generated on the fly. The framework combines operator learning, adjoint algorithmic differentiation, tangent sensitivity equations, random sketching of Jacobian actions, and no-arbitrage constraints. We derive error bounds showing derivative accuracy controls local stress errors, hedging error, and optimizer instability, and that discrete-time hedging error is also governed by second-order (gamma) accuracy. A Black--Scholes network over eight seeds shows a tuned derivative weight cuts vega error by 40\% and delta error by 15\% while modestly improving prices, but not an unsupervised second-order Greek. Heston and Bates random-feature experiments reduce stochastic-volatility and jump-parameter sensitivity errors by 60--76\%. A random-feature DeepONet/Galerkin operator mapping instantaneous-volatility curves to dense price surfaces reduces out-of-sample JVP error by 44\% and price RMSE by 23\% over eight seeds; it also shows derivative consistency alone does not remove no-arbitrage violations, so economic constraints must be imposed explicitly. The framework gives a disciplined route from value-only surrogates to derivative-aware engines that output differentiable instruments for hedging, risk, and control.

q-fin.MF↗