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

← all fields·7 papers on “deep learning” in Statistical ML · 1 week

Adaptive deep nonparametric regression from dependent data under covariate shiftstat.ML

Paper addresses covariate shift in deep learning regression models.

problem Covariate shift in dependent data from different distributions.

method Sparse-penalized deep neural network (SPDNN) estimator for nonparametric regression.

result Adaptive convergence rates for quantile and Huber regression.

covariate shift deep learning nonparametric regression dependent data sparse penalization

2026-07-22abs ↗pdf ↗

Statistical Inference for Rank Allocation in Low-Rank Adaptationstat.ML

StatLoRA uses statistical inference to allocate ranks in LoRA fine-tuning, improving performance.

problem Balancing efficiency, expressiveness, and generalization in LoRA rank allocation.

method Formulates LoRA rank allocation as a statistical hypothesis testing problem, using estimated p-values to determine component retention or pruning.

result StatLoRA achieves comparable or better performance than existing methods under matched rank budgets.

Low-rank adaptation Statistical inference Rank allocation Statistical hypothesis testing Deep learning

2026-07-22abs ↗pdf ↗

Deep Shape Regression for Planar Curves with Multimodal Covariatesstat.ME

Deep model predicts shapes of curves with multiple covariates.

problem Predicting shapes of planar curves with various covariates.

method Deep learning model using complex-valued functions, conditional covariance smoother with modality-specific encoders.

result Model accurately predicts shapes of curves with multimodal covariates.

deep learning shape regression planar curves multimodal covariates Procrustes mean

2026-07-21abs ↗pdf ↗

Deep learning-based prediction of time-resolved adhesive forces in viscoelastic Hertzian contactscs.LG

Deep learning predicts adhesive forces in soft viscoelastic contacts quickly and accurately.

problem Predicting the full time-resolved force trajectory of adhesive soft viscoelastic contacts is computationally expensive and impractical.

method Trained a deep learning model to predict the full force evolution from a prescribed displacement history, using FMS representation and various architectures.

result Best-performing model predicts complete force trajectory with low error metrics and fast inference time.

deep learning adhesive forces viscoelastic contacts time-resolved hysteresis

2026-07-21abs ↗pdf ↗

Value-Monotonicity Matters: A Concordance Loss for Deep Survival Predictioncs.LG

A new concordance loss improves model performance and reliability in survival prediction.

problem Inconsistent evaluation of deep survival models using likelihood losses.

method Proposed a value-monotone concordance loss (SCL) to improve reliability and optimization.

result SCL achieves comparable discrimination and is the best or within one standard deviation of the best C-index across multiple datasets.

survival analysis deep learning likelihood losses concordance index value-monotonicity

2026-07-18abs ↗pdf ↗

Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNetsstat.ML

Dropout and RaM become equivalent in large ResNets as depth and width increase.

problem Improving performance in deep learning models.

method Comparing Dropout and Random Gradient Masking in ResNets.

result Dropout and RaM converge to the same large-scale limiting dynamics in ResNets.

Deep Learning ResNets Dropout Random Gradient Masking Asymptotic Equivalence

2026-07-18abs ↗pdf ↗

A Deep Second-Order Stochastic Residual Method for Fully Nonlinear Parabolic PDEsmath.NA

D2SRM solves complex PDEs using deep learning.

problem High-dimensional, Hessian-dependent fully nonlinear parabolic PDEs.

method Single scalar space-time network generating derivative-consistent approximations trained through residuals and penalties.

result Well-posedness and convergence theory established for globally Lipschitz equations.

Deep learning PDEs Fully nonlinear Brownian residuals Occupation norms

2026-07-18abs ↗pdf ↗