Mohit Kumar — accepted AI-conference papers

2026

Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint)

Mohit Kumar, Alexander Valentinitsch, Magdalena Fuchs, Mathias Brucker, Juliana Bowles, Adnan Husakovic +2

AAAI 2026technical

This paper develops a novel mathematical framework for collaborative learning by means of geometrically inspired kernel machines which includes statements on the bounds of generalisation and approximation errors, and sample complexity. For classification problems, this approach allows us to learn bo

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

GCF: Estimating Unobserved Demand Using Graph Causal Forecasting

Sayantan Basu, Mohit Kumar, Sivaramakrishnan Kaveri

AAAI 2025technical

Time series data, prevalent in fields like medical, e-commerce, finance, etc., is used for forecasting, such as predicting next quarter’s product demand based on past trends. However, some problems necessitate causal models to answer questions like “What the product demand would have been without a…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

On Mitigating the Utility-Loss in Differentially Private Learning: A New Perspective by a Geometrically Inspired Kernel Approach (Abstract Reprint)

Mohit Kumar, Bernhard A. Moser, Lukas Fischer

IJCAI 2024poster

Privacy-utility tradeoff remains as one of the fundamental issues of differentially private machine learning. This paper introduces a geometrically inspired kernel-based approach to mitigate the accuracy-loss issue in classification. In this approach, a representation of the affine hull of given dat…

Cited by 4 Source ↗PDF ↗Scholar ↗