6 papers · 1 filter
Identifiability and Order-Dimension Limits of In-Context Learning on Partial Orders
Faizanuddin Ansari, Debanjan Dutta, Swagatam Das
In-context learning is commonly formalized as inference from examples of a function. Partial orders instead combine transitivity, antisymmetry, and incomparability, so a finite pro…
Sharp Concentration Bounds for Bundle-Valued Statistics on Manifolds
Swagatam Das, Vaclav Snasel
Many geometric statistics and manifold learning pipelines routinely produce observations -- such as tangent vectors or local frames -- whose natural home is a varying family of fib…
Rebalancing with Calibrated Sub-classes (RCS): A Statistical Fusion-based Framework for Robust Imbalanced Classification across Modalities
Priyobrata Mondal, Faizanuddin Ansari, Swagatam Das
Class imbalance, where certain classes have insufficient data, poses a critical challenge for robust classification, often biasing models toward majority classes. Distribution cali…
APFEx: Adaptive Pareto Front Explorer for Intersectional Fairness
Priyobrata Mondal, Faizanuddin Ansari, Swagatam Das
Ensuring fairness in machine learning models is critical, especially when biases compound across intersecting protected attributes like race, gender, and age. While existing method…
Assessing the Limits of In-Context Learning beyond Functions using Partially Ordered Relation
Debanjan Dutta, Faizanuddin Ansari, Swagatam Das
Generating rational and generally accurate responses to tasks, often accompanied by example demonstrations, highlights Large Language Model's (LLM's) remarkable In-Context Learning…
Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning
Srinjoy Roy, Swagatam Das
Accounting for the uncertainty of value functions boosts exploration in Reinforcement Learning (RL). Our work introduces Maximum Mean Discrepancy Q-Learning (MMD-QL) to improve Was…