65 citations · 143 across the 21 of their papers we have counts for
26 papers
Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve
Denys Pushkin, Albert Q. Jiang, Aryo Lotfi +2
Chain-of-Thought (CoT) prompting remains the standard baseline for evaluating models' reasoning abilities. Originally, this technique was introduced to elicit step-by-step reasonin…
Recovering Assignments with One-Sided Noise
Cassandra Marcussen, Elchanan Mossel, Colin Sandon
We study the query complexity of recovering a planted assignment from a random constraint-satisfaction instance with one-sided noise. We consider the following 1-CNF recovery probl…
Tensor Reed-Muller Codes: Achieving Capacity with Quasilinear Decoding Time
Emmanuel Abbe, Colin Sandon, Oscar Sprumont
Define the codewords of the Tensor Reed-Muller code to be the evaluation vectors of all multivariate polynomials in the variables $\le…
Finding Planted Cycles in a Random Graph
Julia Gaudio, Colin Sandon, Jiaming Xu +1
In this paper, we study the problem of finding a collection of planted cycles in an \ER random graph , in analogy to the famous Planted Clique Problem.…
Reed-Muller Codes for Quantum Pauli and Multiple Access Channels
Dina Abdelhadi, Colin Sandon, Emmanuel Abbe +1
Reed-Muller (RM) codes have undergone significant analytical advancements over the past decade, particularly for binary memoryless symmetric (BMS) channels. We extend the scope of…
Phase Transitions in Planted k-Factor Recovery
Julia Gaudio, Colin Sandon, Jiaming Xu +1
This paper studies the problem of inferring a -factor, specifically a spanning -regular graph, planted within an Erdos-Renyi random graph . We show that as the aver…
Polynomial Freiman-Ruzsa, Reed-Muller codes and Shannon capacity
Emmanuel Abbe, Colin Sandon, Vladyslav Shashkov +1
In 1948, Shannon used a probabilistic argument to show the existence of codes achieving a maximal rate defined by the channel capacity. In 1954, Muller and Reed introduced a simple…
How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
Emmanuel Abbe, Samy Bengio, Aryo Lotfi +2
Can Transformers predict new syllogisms by composing established ones? More generally, what type of targets can be learned by such models from scratch? Recent works show that Trans…
Reed-Muller codes have vanishing bit-error probability below capacity: a simple tighter proof via camellia boosting
Emmanuel Abbe, Colin Sandon
This paper shows that a class of codes such as Reed-Muller (RM) codes have vanishing bit-error probability below capacity on symmetric channels. The proof relies on the notion of `…
A proof that Reed-Muller codes achieve Shannon capacity on symmetric channels
Emmanuel Abbe, Colin Sandon
Reed-Muller codes were introduced in 1954, with a simple explicit construction based on polynomial evaluations, and have long been conjectured to achieve Shannon capacity on symmet…
The Power of an Adversary in Glauber Dynamics
Byron Chin, Ankur Moitra, Elchanan Mossel +1
Glauber dynamics are a natural model of dynamics of dependent systems. While originally introduced in statistical physics, they have found important applications in the study of so…
The Power of Two Matrices in Spectral Algorithms for Community Recovery
Souvik Dhara, Julia Gaudio, Elchanan Mossel +1
Spectral algorithms are some of the main tools in optimization and inference problems on graphs. Typically, the graph is encoded as a matrix and eigenvectors and eigenvalues of the…
Spectral Algorithms Optimally Recover Planted Sub-structures
Souvik Dhara, Julia Gaudio, Elchanan Mossel +1
Spectral algorithms are an important building block in machine learning and graph algorithms. We are interested in studying when such algorithms can be applied directly to provide…
On the Power of Differentiable Learning versus PAC and SQ Learning
Emmanuel Abbe, Pritish Kamath, Eran Malach +2
We study the power of learning via mini-batch stochastic gradient descent (SGD) on the population loss, and batch Gradient Descent (GD) on the empirical loss, of a differentiable m…
Spectral Recovery of Binary Censored Block Models
Souvik Dhara, Julia Gaudio, Elchanan Mossel +1
Community detection is the problem of identifying community structure in graphs. Often the graph is modeled as a sample from the Stochastic Block Model, in which each vertex belong…
Spoofing Generalization: When Can't You Trust Proprietary Models?
Ankur Moitra, Elchanan Mossel, Colin Sandon
In this work, we study the computational complexity of determining whether a machine learning model that perfectly fits the training data will generalizes to unseen data. In partic…
Learning to Sample from Censored Markov Random Fields
Ankur Moitra, Elchanan Mossel, Colin Sandon
We study learning Censor Markov Random Fields (abbreviated CMRFs). These are Markov Random Fields where some of the nodes are censored (not observed). We present an algorithm for l…
Poly-time universality and limitations of deep learning
Emmanuel Abbe, Colin Sandon
The goal of this paper is to characterize function distributions that deep learning can or cannot learn in poly-time. A universality result is proved for SGD-based deep learning an…
Parallels Between Phase Transitions and Circuit Complexity?
Ankur Moitra, Elchanan Mossel, Colin Sandon
In many natural average-case problems, there are or there are believed to be critical values in the parameter space where the structure of the space of solutions changes in a funda…
Provable limitations of deep learning
Emmanuel Abbe, Colin Sandon
As the success of deep learning reaches more grounds, one would like to also envision the potential limits of deep learning. This paper gives a first set of results proving that ce…
Graph powering and spectral robustness
Emmanuel Abbe, Enric Boix, Peter Ralli +1
Spectral algorithms, such as principal component analysis and spectral clustering, typically require careful data transformations to be effective: upon observing a matrix , one…
Detection in the stochastic block model with multiple clusters: proof of the achievability conjectures, acyclic BP, and the information-computation gap
Emmanuel Abbe, Colin Sandon
In a paper that initiated the modern study of the stochastic block model, Decelle et al., backed by Mossel et al., made the following conjecture: Denote by the number of balanc…
Recovering communities in the general stochastic block model without knowing the parameters
Emmanuel Abbe, Colin Sandon
Most recent developments on the stochastic block model (SBM) rely on the knowledge of the model parameters, or at least on the number of communities. This paper introduces efficien…
Community detection in general stochastic block models: fundamental limits and efficient recovery algorithms
Emmanuel Abbe, Colin Sandon
New phase transition phenomena have recently been discovered for the stochastic block model, for the special case of two non-overlapping symmetric communities. This gives raise in…