collaborators

6 papers

cs.LG2026

Representation Alignment Rests on Linear Structure

Kiril Bangachev, Guy Bresler, Yury Polyanskiy

We investigate the Platonic Representation Hypothesis (PRH) through a tripartite statistical framework of representations: signal, bias, and noise. {1) Signal:} We propose that Pla…

cs.LG2026

Is Dimensionality a Barrier for Retrieval Models?

Kiril Bangachev, Guy Bresler, Jonathan Kogan +1

Why does the low dimensionality of representations, typically , not prevent modern embedding-based retrieval models from scaling to billions, or even trillions, of d…

cs.LG2026

Global Minimizers of Sigmoid Contrastive Loss

Kiril Bangachev, Guy Bresler, Iliyas Noman +1

The meta-task of obtaining and aligning representations through contrastive pretraining is steadily gaining importance since its introduction in CLIP and ALIGN. In this paper we th…

math.ST2025

Graph Quasirandomness for Hypothesis Testing of Stochastic Block Models

Kiril Bangachev, Guy Bresler

The celebrated theorem of Chung, Graham, and Wilson on quasirandom graphs implies that if the 4-cycle and edge counts in a graph are both close to their typical number in $\mat…

math.CO2025

Partial and Exact Recovery of a Random Hypergraph from its Graph Projection

Guy Bresler, Chenghao Guo, Yury Polyanskiy +1

Consider a -uniform random hypergraph on vertices in which hyperedges are included iid so that the average degree is . The projection of a hypergraph is a graph on the…

math.ST2025

Thresholds for Reconstruction of Random Hypergraphs From Graph Projections

Guy Bresler, Chenghao Guo, Yury Polyanskiy

The graph projection of a hypergraph is a simple graph with the same vertex set and with an edge between each pair of vertices that appear in a hyperedge. We consider the problem o…