5 citations · 7 across the 7 of their papers we have counts for
8 papers
How Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences
Mariia Seleznova
We study signal propagation in linear recurrent models at finite width. While existing signal propagation theory relies predominantly on the infinite-width limit, it remains unclea…
From Seeds to Semantics: Measuring Semantic Accessibility in Deterministic Diffusion Models
Wei Wei, Yizhou Zeng, Kuntian Chen +3
Diffusion models generate samples through a sequence of learned denoising steps, and recent work has studied how semantic structure appears along this sampling process. We study th…
Revisiting Glorot Initialization for Long-Range Linear Recurrences
Noga Bar, Mariia Seleznova, Yotam Alexander +2
Proper initialization is critical for Recurrent Neural Networks (RNNs), particularly in long-range reasoning tasks, where repeated application of the same weight matrix can cause v…
GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
Mariia Seleznova, Hung-Hsu Chou, Claudio Mayrink Verdun +1
We introduce GradPCA, an Out-of-Distribution (OOD) detection method that exploits the low-rank structure of neural network gradients induced by Neural Tangent Kernel (NTK) alignmen…
Neural (Tangent Kernel) Collapse
Mariia Seleznova, Dana Weitzner, Raja Giryes +2
This work bridges two important concepts: the Neural Tangent Kernel (NTK), which captures the evolution of deep neural networks (DNNs) during training, and the Neural Collapse (NC)…
Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization
Mariia Seleznova, Gitta Kutyniok
Neural Tangent Kernel (NTK) is widely used to analyze overparametrized neural networks due to the famous result by Jacot et al. (2018): in the infinite-width limit, the NTK is dete…
Analyzing Finite Neural Networks: Can We Trust Neural Tangent Kernel Theory?
Mariia Seleznova, Gitta Kutyniok
Neural Tangent Kernel (NTK) theory is widely used to study the dynamics of infinitely-wide deep neural networks (DNNs) under gradient descent. But do the results for infinitely-wid…
Towards Large-Scale Exploratory Search over Heterogeneous Sources
Mariia Seleznova, Anton Belyy, Aleksei Sholokhov
Since time immemorial, people have been looking for ways to organize scientific knowledge into some systems to facilitate search and discovery of new ideas. The problem was partial…