2 papers
cs.LG2026
When Softmax Fails at the Top: Extreme Value Corrections for InfoNCE
Melihcan Erol, Suat Evren, Oktay Ozel +3
InfoNCE is the standard contrastive learning objective, but its softmax form is not only a computational convenience: it also encodes a statistical assumption about how the top-sco…
cs.LG2026
When Learning Hurts: Fixed-Pole RNN for Real-Time Online Training
Alexander Morgan, Ummay Sumaya Khan, Lingjia Liu +1
Recurrent neural networks (RNNs) can be interpreted as discrete-time state-space models, where the state evolution corresponds to an infinite-impulse-response (IIR) filtering opera…