Kiril Bangachev

activity

20182026

most citedRandom Algebraic Graphs and Their Convergence to Erdos-Renyi

2 citations · 4 across the 10 of their papers we have counts for

collaborators

13 papers

cs.CV2026

PRIMFLOW: Learning Trajectory Primitives for Few-Step Distillation

Hongyi Fang, Benjia Zhou

Few-step trajectory distillation aims to learn accurate global updates from dense local supervision along a teacher's sampling trajectory. Existing approaches construct within-step…

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 $d \approx 1000$ , not prevent modern embedding-based retrieval models from scaling to billions, or even trillions, of d…

cs.LG2025

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 $G$ are both close to their typical number in $\mat…

cs.CC2024★ 1 cited

Near-Optimal Time-Sparsity Trade-Offs for Solving Noisy Linear Equations

Kiril Bangachev, Guy Bresler, Stefan Tiegel +1

We present a polynomial-time reduction from solving noisy linear equations over $Z / q Z$ in dimension $Θ (k lo g n / poly (lo g k, lo g q, lo g lo g n))$ with a un…

math.PR2024★ 1 cited

Sandwiching Random Geometric Graphs and Erdos-Renyi with Applications: Sharp Thresholds, Robust Testing, and Enumeration

Kiril Bangachev, Guy Bresler

The distribution $RGG (n, S^{d - 1}, p)$ is formed by sampling independent vectors ${V_{i}}_{i = 1}^{n}$ uniformly on $S^{d - 1}$ and placing an edge between pair…

math.ST2024

On The Fourier Coefficients of High-Dimensional Random Geometric Graphs

Kiril Bangachev, Guy Bresler

The random geometric graph $RGG (n, S^{d - 1}, p)$ is formed by sampling $n$ i.i.d. vectors ${V_{i}}_{i = 1}^{n}$ uniformly on $S^{d - 1}$ and placing an edge be…

math.ST2023

Detection of $L_{\infty}$ Geometry in Random Geometric Graphs: Suboptimality of Triangles and Cluster Expansion

Kiril Bangachev, Guy Bresler

In this paper we study the random geometric graph $RGG (n, T^{d}, Unif, σ_{p}^{q}, p)$ with $L_{q}$ distance where each vertex is sampled uniformly from the $d$ -dimen…

math.PR2023★ 2 cited

Random Algebraic Graphs and Their Convergence to Erdos-Renyi

Kiril Bangachev, Guy Bresler

A random algebraic graph is defined by a group $G$ with a uniform distribution over it and a connection $σ : G ⟶ [0, 1]$ with expectation $p,$ satisfying $σ (g) = σ (g^{- 1}) .$ …

cs.GT2023

q-Partitioning Valuations: Exploring the Space Between Subadditive and Fractionally Subadditive Valuations

Kiril Bangachev, S. Matthew Weinberg

For a set $M$ of $m$ elements, we define a decreasing chain of classes of normalized monotone-increasing valuation functions from $2^{M}$ to $R_{\geq 0}$ , parameterized by a…

math.CO2021

On the Asymmetric Generalizations of Two Extremal Questions on Friends-and-Strangers Graphs

Kiril Bangachev

For two graphs $X$ and $Y$ with vertex sets $V (X)$ and $V (Y)$ of the same cardinality $n,$ the friends-and-strangers graph $FS (X, Y)$ was recently defined by Defant and Kra…

math.CO2018

Enumerative and Structural Aspects Of Anagrams Without Fixed Letters

Kiril Bangachev

For the word $ω = x_{1} 11 \dots 1 x_{2} 22 \dots 2 \dots x_{n} nn \dots n,$ denote by $A (x_{1}, x_{2}, \dots, x_{n})$ the number of its anag…

PRIMFLOW: Learning Trajectory Primitives for Few-Step Distillation

Representation Alignment Rests on Linear Structure

Is Dimensionality a Barrier for Retrieval Models?

Global Minimizers of Sigmoid Contrastive Loss

Graph Quasirandomness for Hypothesis Testing of Stochastic Block Models

Near-Optimal Time-Sparsity Trade-Offs for Solving Noisy Linear Equations

Sandwiching Random Geometric Graphs and Erdos-Renyi with Applications: Sharp Thresholds, Robust Testing, and Enumeration

On The Fourier Coefficients of High-Dimensional Random Geometric Graphs

Detection of L∞​ Geometry in Random Geometric Graphs: Suboptimality of Triangles and Cluster Expansion

Random Algebraic Graphs and Their Convergence to Erdos-Renyi

q-Partitioning Valuations: Exploring the Space Between Subadditive and Fractionally Subadditive Valuations

On the Asymmetric Generalizations of Two Extremal Questions on Friends-and-Strangers Graphs

Enumerative and Structural Aspects Of Anagrams Without Fixed Letters

Detection of $L_{\infty}$ Geometry in Random Geometric Graphs: Suboptimality of Triangles and Cluster Expansion