68 citations · 166 across the 15 of their papers we have counts for
15 papers
Towards understanding neural collapse in supervised contrastive learning with the information bottleneck method
Siwei Wang, Stephanie E Palmer
Neural collapse describes the geometry of activation in the final layer of a deep neural network when it is trained beyond performance plateaus. Open questions include whether neur…
Representational drift changes the encoding of fast and slow-varying natural scene features differently
Siwei Wang, Elizabeth A de Laittre, Jason MacLean +1
Representational drift refers to an unstable mapping between neural activity and input sensory or output behavioral variables. While much work has focused on the effect of represen…
Multi-Relevance: Coexisting but Distinct Notions of Scale in Large Systems
Adam G. Kline, Stephanie E. Palmer
Renormalization group (RG) methods are emerging as tools in biology and computer science to support the search for simplifying structure in distributions over high-dimensional spac…
Emergent scale-free networks
Christopher W. Lynn, Caroline M. Holmes, Stephanie E. Palmer
Many complex systems--from social and communication networks to biological networks and the Internet--are thought to exhibit scale-free structure. However, prevailing explanations…
Gaussian Information Bottleneck and the Non-Perturbative Renormalization Group
Adam G. Kline, Stephanie E. Palmer
The renormalization group (RG) is a class of theoretical techniques used to explain the collective physics of interacting, many-body systems. It has been suggested that the RG form…
Inferring couplings in networks across order-disorder phase transitions
Vudtiwat Ngampruetikorn, Vedant Sachdeva, Johanna Torrence +3
Statistical inference is central to many scientific endeavors, yet how it works remains unresolved. Answering this requires a quantitative understanding of the intrinsic interplay…