Stefano Sarao Mannelli
11 papers · 2019–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
๐ Interdisciplinary Bridge ๐งญ Keyword Pioneer ๐ฃ Hot Topic Early Bird ๐บ๏ธ Taxonomy Completionist (15) ๐ Conference Polyglot (3)
๐
Academic Marathon
(6)
๐
Cross-Pollinator
(13)
๐
Keyword Champion
(2)
๐
Century Club
(11)
โ
The Questioner
(2)
Conferences
NIPS (5)
ICML (4)
ICLR (2)
Top co-authors
Keywords
non-convex optimization
(3)
gradient flow
(2)
landscape analysis
(2)
spurious minima
(2)
gradient descent
(2)
phase retrieval
(1)
gaussian mixture model
(1)
sgd dynamics
(1)
quadratic activation
(1)
momentum method
(1)
nesterov acceleration
(1)
gradient descent dynamics
(1)
message passing algorithm
(1)
saddle point
(1)
task similarity
(1)
local minima
(1)
teacher-student setup
(1)
spurious feature
(1)
node activation
(1)
spiked tensor model
(1)
Papers
A Theory of Initialisation's Impact on Specialisation
ICLR 2025
Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
ICLR 2025
Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks
ICML 2024
Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training
NIPS 2024
Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning
ICML 2024
Maslowโs Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation
ICML 2022
Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems
NIPS 2021
Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions
NIPS 2020
Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval
NIPS 2020
Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models
ICML 2019
Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models
NIPS 2019