3 papers
cs.LG2026
Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers
Andrei Chertkov, Artem Basharin, Mikhail Saygin +3
The growing demand for energy-efficient, high-performance AI systems has led to increased attention on alternative computing platforms (e.g., photonic, neuromorphic) due to their p…
cs.IR2024
Scalable Cross-Entropy Loss for Sequential Recommendations with Large Item Catalogs
Gleb Mezentsev, Danil Gusak, Ivan Oseledets +1
Scalability issue plays a crucial role in productionizing modern recommender systems. Even lightweight architectures may suffer from high computational overload due to intermediate…
cs.IR2024
RECE: Reduced Cross-Entropy Loss for Large-Catalogue Sequential Recommenders
Danil Gusak, Gleb Mezentsev, Ivan Oseledets +1
Scalability is a major challenge in modern recommender systems. In sequential recommendations, full Cross-Entropy (CE) loss achieves state-of-the-art recommendation quality but con…