activity
20242026
collaborators

7 papers

cs.LG2026

MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning

Ankita Awasthi, Marco Apolinario, Kaushik Roy

In Online Continual Learning (OCL), a neural network sequentially learns from a non-stationary data stream in a single-pass with access only to a limited memory replay buffer. This…

cs.LG2026

LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning

Marco Paul E. Apolinario, Kaushik Roy

On-device learning is essential for personalization, privacy, and long-term adaptation in resource-constrained environments. Achieving this requires efficient learning, both fine-t…

cs.LG2025

Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning

Arani Roy, Marco P. Apolinario, Shristi Das Biswas +1

Training deep neural networks (DNNs) with backpropagation (BP) achieves state-of-the-art accuracy but requires global error propagation and full parameterization, leading to substa…

cs.LG2025

CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning

Marco Paul E. Apolinario, Sakshi Choudhary, Kaushik Roy

Continual learning (CL) - the ability to progressively acquire and integrate new concepts - is essential to intelligent systems to adapt to dynamic environments. However, deep neur…

cs.NE2025

TESS: A Scalable Temporally and Spatially Local Learning Rule for Spiking Neural Networks

Marco Paul E. Apolinario, Kaushik Roy, Charlotte Frenkel

The demand for low-power inference and training of deep neural networks (DNNs) on edge devices has intensified the need for algorithms that are both scalable and energy-efficient.…

cs.NE2024

LLS: Local Learning Rule for Deep Neural Networks Inspired by Neural Activity Synchronization

Marco Paul E. Apolinario, Arani Roy, Kaushik Roy

Training deep neural networks (DNNs) using traditional backpropagation (BP) presents challenges in terms of computational complexity and energy consumption, particularly for on-dev…