Florent Krzakala
where else to find them
what they talk about
where they keep going back
no series more than once — all 7 in the filters
on a stage with
- Lenka Zdeborova5×
- Adam R. Klivansonce
- Fanny Yangonce
all 7 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Panel on the future of scientific research and education | Unknown Futures of Generalization 2024 | 2024-12-02 |
A live panel debates which research skills survive widespread LLM use and gives concrete examples: a student-run “Resurrected Scientists” ChatGPT experiment… | ||
| How neural networks learns simple functions? | Unknown Futures of Generalization 2024 | 2024-12-02 |
Examines learning of multi‑index targets on Gaussian data and shows concrete failure modes and fixes: random features = polynomial fitting so kernels or lazy… | ||
| To Be (Hard) or Not Be:... | Rigorous Evidence for Information-Computation Trade-offs | 2021-09-13 |
Defines the spiked matrix-tensor model (rank‑one vector, noisy matrix plus p=3 tensor), computes the Bayes-optimal MMSE from the limiting free energy and… | ||
| Phase Retrieval in High Dimensions: Statistical and Computational Phase Transitions | Computational Phase Transitions (Simons Institute, 2020) | 2020-09-21 |
Random Gaussian measurements require weak threshold m/d = β/2 (real 1/2, complex 1) and strong threshold m/d = β (real 1, complex 2); orthogonal ensembles push… | ||
| Statistical Physics and Computation in High Dimension | Probability, Geometry, and Computation in High Dimensions Boot Camp (Simons Institute, Fall 2020) | 2020-08-19 |
Computes typical minimal energy per spin for the random‑field Ising model in the n→∞ limit and shows the average free energy equals the extremum of a replica… | ||
| Statistical Physics and Computation in High Dimension | Probability, Geometry, and Computation in High Dimensions Boot Camp (Simons Institute, Fall 2020) | 2020-08-19 |
Lecture contrasts exact limits and practical algorithms: replica and cavity methods give asymptotic mutual information and an information-theoretic recovery… | ||
| Statistical Physics and Computation in High Dimension | Probability, Geometry, and Computation in High Dimensions Boot Camp (Simons Institute, Fall 2020) | 2020-08-19 |
Analyzes teacher-student neural ensembles (committee machines) with analytic replica solution and matching simulations to produce exact learning curves as a… | ||
| Statistical Physics and Computation in High Dimension | Probability, Geometry, and Computation in High Dimensions Boot Camp (Simons Institute, Fall 2020) | 2020-08-19 |
Covers the generalized linear model with five concrete cases: perceptron storage capacity (spherical capacity = 2, binary perceptron conjectured threshold ≈… | ||
| Phase Transitions in Low-Rank Matrix Estimation | Random Instances and Phase Transitions (Simons Institute, 2016) | 2016-05-02 |
Florent Krzakala, École Normale Supérieure Paris
Random Instances and Phase Transitions
https://simons.berkeley.edu/talks/florent-krzakala-2016-05-03 | ||
| The Partition Function, Sampling and Equilibration in Physics | Counting Complexity and Phase Transitions Boot Camp | 2016-01-26 |
Physicist framing focuses on the free energy as log Z per particle and uses Monte Carlo heuristics to locate sharp phase transitions; empirically mixing time… | ||
| Sparse Superposition Codes for the AWGN Channel, Message Passing, Replica and Spatial Coupling | Coding: From Practice to Theory | 2015-02-19 |
Sparse superposition codes encode messages as L sections of size B with one nonzero entry, then multiply by a random or Hadamard matrix and send over AWGN… | ||
| nothing matches | ||