Search Results for author:
Found 11 papers, 0 papers with code
The Garden of Forking Paths: Observing Dynamic Parameters Distribution in Large Language Models
A substantial gap persists in understanding the reasons behind the exceptional performance of the Transformer architecture in NLP.
A Short Review on Novel Approaches for Maximum Clique Problem: from Classical algorithms to Graph Neural Networks and Quantum algorithms
This manuscript provides a comprehensive review of the Maximum Clique Problem, a computational problem that involves finding subsets of vertices in a graph that are all pairwise adjacent to each other.
Engineered Ordinary Differential Equations as Classification Algorithm (EODECA): thorough characterization and testing
EODECA (Engineered Ordinary Differential Equations as Classification Algorithm) is a novel approach at the intersection of machine learning and dynamical systems theory, presenting a unique framework for classification tasks [1].
Complex Recurrent Spectral Network
This paper presents a novel approach to advancing artificial intelligence (AI) through the development of the Complex Recurrent Spectral Network ($\mathbb{C}$-RSN), an innovative variant of the Recurrent Spectral Network (RSN) model.
A Bridge between Dynamical Systems and Machine Learning: Engineered Ordinary Differential Equations as Classification Algorithm (EODECA)
Recognizing the deep parallels between dense neural networks and dynamical systems, particularly in the light of non-linearities and successive transformations, this manuscript introduces the Engineered Ordinary Differential Equations as Classification Algorithms (EODECAs).
Stochastic Gradient Descent-like relaxation is equivalent to Glauber dynamics in discrete optimization and inference problems
Is Stochastic Gradient Descent (SGD) substantially different from Glauber dynamics?
Phase transitions in the mini-batch size for sparse and dense two-layer neural networks
This work presents a systematic attempt at understanding the role of the mini-batch size in training two-layer neural networks.
Nonequilibrium Monte Carlo for unfreezing variables in hard combinatorial optimization
In particular, for 90% of random 4-SAT instances we find solutions that are inaccessible for the best specialized deterministic algorithm known as Survey Propagation (SP) with an order of magnitude improvement in the quality of solutions for the hardest 10% instances.
Learning from Survey Propagation: a Neural Network for MAX-E-$3$-SAT
This paper presents a new algorithm for computing approximate solutions in ${\Theta(N})$ for the Maximum Exact 3-Satisfiability (MAX-E-$3$-SAT) problem by using deep learning methodology.
Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes
The main idea is to construct a deep network which is trained from the samples of discrete stochastic differential equations underlying Kolmogorov's equation.
The backtracking survey propagation algorithm for solving random K-SAT problems
Discrete combinatorial optimization has a central role in many scientific disciplines, however, for hard problems we lack linear time algorithms that would allow us to solve very large instances.
