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

4 results for “near-deterministic”

Parameter uncertainties for imperfect surrogate models in the low-noise regimestat.ML

Bayesian regression underestimates parameter uncertainties in noisy models.

problem Parameter uncertainties are underestimated in Bayesian regression for imperfect models.

method Analyzed and designed an ansatz to correct for misspecification in near-deterministic surrogate models.

result Posterior distributions must cover all training points to avoid divergent generalization error.

Bayesian regression parameter uncertainties misspecified models near-deterministic generalization error

2024-02-02abs ↗pdf ↗

Compositional uncertainty in deep Gaussian processesstat.ML

Gaussian processes (GPs) are nonparametric priors over functions. Fitting a GP implies computing a posterior distribution of functions consistent with the observed data. Similarly, deep Gaussian processes (DGPs) should allow us to compute a posterior distribution of compositions of multiple functions giving rise to the…

2019-09-17abs ↗pdf ↗

Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithmcs.LG

Paper analyzes NAC with neural networks for efficient policy optimization.

problem Improving sample and iteration complexity in policy optimization.

method Entropy regularization, averaging, neural network approximation, and optimization techniques.

result Entropy regularization and averaging ensure stability and sharp sample complexity bounds.

natural actor-critic neural networks policy optimization finite-time analysis sample complexity

2022-06-02abs ↗pdf ↗

Embrace the Gap: VAEs Perform Independent Mechanism Analysisstat.ML

VAEs improve representation learning by inverting the data-generating process through self-consistency.

problem VAEs struggle to invert the data-generating process, yet often succeed in representation learning.

method Studied VAEs in the limit of near-deterministic decoders, proving self-consistency and showing ELBO convergence to a regularized log-likelihood.

result VAEs can perform independent mechanism analysis (IMA), recovering true latent factors under specific conditions.

VAEs representation learning independent mechanism analysis self-consistency log-likelihood

2022-06-06abs ↗pdf ↗