collaborators
Showing stat.MLShow all

8 papers · 1 filter

stat.ML2026

From Sublinear to Linear: Local Convergence in Finite-Width Networks via Locally Polyak-Lojasiewicz Regions

Agnideep Aich, Ashit Baran Aich, Bruce Wade

We study local linear convergence of gradient descent for finite-width feedforward networks under the squared empirical loss. Prior work shows that GD can remain confined to a Loca…

stat.ML2026

The Minimax Lower Bound of Kernel Stein Discrepancy Estimation

Jose Cribeiro-Ramallo, Agnideep Aich, Florian Kalinke +2

Kernel Stein discrepancies (KSDs) have emerged as a powerful tool for quantifying goodness-of-fit over the last decade, featuring numerous successful applications. To the best of o…

stat.ML2026

Temporal Conformal Prediction (TCP): A Distribution-Free Statistical and Machine Learning Framework for Adaptive Risk Forecasting

Agnideep Aich, Ashit Baran Aich, Dipak C. Jain

We propose \textbf{Temporal Conformal Prediction (TCP)}, a distribution-free framework for constructing well-calibrated prediction intervals in nonstationary time series. TCP coupl…

stat.ML2026

Bag of Coins: A Statistical Probe into Neural Confidence Structures

Agnideep Aich, Sameera Hewage, Md Monzur Murshed +2

Modern neural networks often produce miscalibrated confidence scores and struggle to detect out-of-distribution (OOD) inputs, while most existing methods post-process outputs witho…

stat.ML2026

Copula-Stein Discrepancy: A Generator-Based Stein Operator for Archimedean Dependence

Agnideep Aich, Ashit Baran Aich

Kernel Stein discrepancies (KSDs) are widely used for goodness-of-fit testing, but standard KSDs can be insensitive to higher-order dependence features such as tail dependence. We…

stat.ML2025

Copula Discrepancy: Benchmarking Dependence Structure

Agnideep Aich, Ashit Baran Aich

We study a simple statistic for benchmarking how well a sample preserves a known bivariate dependence structure. Given a target copula family (Clayton or Gumbel) and parameter $θ_…