Disordered systems insights on computational hardness
In this review article we discuss connections between the physics of disordered systems,
phase transitions in inference problems, and computational hardness. We introduce two …
phase transitions in inference problems, and computational hardness. We introduce two …
Sampling with flows, diffusion, and autoregressive neural networks from a spin-glass perspective
Recent years witnessed the development of powerful generative models based on flows,
diffusion, or autoregressive neural networks, achieving remarkable success in generating …
diffusion, or autoregressive neural networks, achieving remarkable success in generating …
Reducibility and statistical-computational gaps from secret leakage
M Brennan, G Bresler - Conference on Learning Theory, 2020 - proceedings.mlr.press
Inference problems with conjectured statistical-computational gaps are ubiquitous
throughout modern statistics, computer science, statistical physics and discrete probability …
throughout modern statistics, computer science, statistical physics and discrete probability …
Inference of dynamic hypergraph representations in temporal interaction data
A Kirkley - Physical Review E, 2024 - APS
A range of systems across the social and natural sciences generate data sets consisting of
interactions between two distinct categories of items at various instances in time. Online …
interactions between two distinct categories of items at various instances in time. Online …
Fundamental limits to learning closed-form mathematical models from data
O Fajardo-Fontiveros, I Reichardt… - Nature …, 2023 - nature.com
Given a finite and noisy dataset generated with a closed-form mathematical model, when is
it possible to learn the true generating model from the data alone? This is the question we …
it possible to learn the true generating model from the data alone? This is the question we …
Marvels and pitfalls of the langevin algorithm in noisy high-dimensional inference
Gradient-descent-based algorithms and their stochastic versions have widespread
applications in machine learning and statistical inference. In this work, we carry out an …
applications in machine learning and statistical inference. In this work, we carry out an …
Community detection in bipartite networks with stochastic block models
In bipartite networks, community structures are restricted to being disassortative, in that
nodes of one type are grouped according to common patterns of connection with nodes of …
nodes of one type are grouped according to common patterns of connection with nodes of …
Passed & spurious: Descent algorithms and local minima in spiked matrix-tensor models
In this work we analyse quantitatively the interplay between the loss landscape and
performance of descent algorithms in a prototypical inference problem, the spiked matrix …
performance of descent algorithms in a prototypical inference problem, the spiked matrix …
Exact phase transitions for stochastic block models and reconstruction on trees
In this paper, we rigorously establish the predictions in ground breaking work in statistical
physics by Decelle, Krzakala, Moore, Zdeborová (2011) regarding the block model, in …
physics by Decelle, Krzakala, Moore, Zdeborová (2011) regarding the block model, in …
Limits and performances of algorithms based on simulated annealing in solving Sparse hard inference problems
The planted-coloring problem is a prototypical inference problem for which thresholds for
Bayes-optimal algorithms, like belief propagation (BP), can be computed analytically. In this …
Bayes-optimal algorithms, like belief propagation (BP), can be computed analytically. In this …