Ankur Moitra
where else to find them
no profile links on file
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 12 in the filters
on a stage with
all 5 in the filters
who talks about the same things
- Anima Anandkumar7 talks
- Saman Amarasinghe13 talks
- Makrand Sinha5 talks
- Animashree Anandkumar5 talks
- Emmanuel Abbe5 talks
- Yuval Filmus9 talks
| title | conference | date |
|---|---|---|
| Debate: Sparks versus embers | Unknown Futures of Generalization 2024 | 2024-12-02 |
Motion: whether current LLM scaling plus realistic post-training can produce new proof techniques to settle problems like P≠NP. Panelists present concrete… | ||
| Learning from Dynamics | Joint IFML/MPG Symposium 2024 | 2024-11-19 |
Given one long input-output trajectory, the paper proves polynomial-time parameter recovery for linear dynamical systems under marginal stability plus bounded… | ||
| When do dependencies in your data help? | Emerging Generalization Settings 2024 | 2024-09-09 |
Assumes samples come from Glauber dynamics and proves bounded‑degree k‑wise Markov random fields are learnable in roughly n^2 log n time from a single n log n… | ||
| How Do Transformers Work? | Special Year on Large Language Models and Transformers, Part 1 Boot Camp | 2024-09-04 |
Explains transformers as an encoder–decoder stack that replaces huge n‑gram parameter blowups (V^4 for a 4‑gram) with learned vector word embeddings (hundreds… | ||
| Learning Restricted Boltzman Machines | Algorithmic Aspects of Causal Inference 2022 | 2022-03-18 |
Proves bounded‑degree RBMs exactly capture order‑T binary Markov random fields, giving a sharp representational characterization; shows improper learning of… | ||
| Recent Progress in High-Dimensional Learning | Probability, Geometry, and Computation in High Dimensions Boot Camp (Simons Institute, Fall 2020) | 2020-08-19 |
Argues that low‑rank tensor decompositions uniquely recover latent factors under mild linear‑independence conditions and gives an explicit spectral method… | ||
| Recent Progress in High-Dimensional Learning | Probability, Geometry, and Computation in High Dimensions Boot Camp (Simons Institute, Fall 2020) | 2020-08-19 |
1D robust estimation uses the median absolute deviation to get O(ε) TV guarantees, but high dimensions face hardness: the Tukey median is robust but NP‑hard… | ||
| Recent Progress in High-Dimensional Learning | Probability, Geometry, and Computation in High Dimensions Boot Camp (Simons Institute, Fall 2020) | 2020-08-19 |
Shows polynomial‑time algorithms that learn half‑spaces under Massart noise up to error η+ε, first via an improper partitioned classifier and now via a proper… | ||
| Recent Progress in High-Dimensional Learning | Probability, Geometry, and Computation in High Dimensions Boot Camp (Simons Institute, Fall 2020) | 2020-08-19 |
Provable algorithms reconstruct mixtures of Airy disks from photon samples: for any fixed K a polynomial-time algorithm recovers centers to accuracy ε given… | ||
| LP/SDP Hierarchies and Sum of Squares Proofs 1 | Bridging Continuous and Discrete Optimization Boot Camp 2017 | 2017-08-21 |
Explains that nonnegativity checks reduce to semidefinite programming by writing a polynomial as a quadratic form over a chosen monomial basis and searching… | ||
| LP/SDP Hierarchies and Sum of Squares Proofs 2 | Bridging Continuous and Discrete Optimization Boot Camp 2017 | 2017-08-21 |
Real infeasibility certificates appear as an f + g = -1 certificate with f in the ideal of equations and g in the cone generated by inequalities; bounding the… | ||
| LP/SDP Hierarchies and Sum of Squares Proofs 3 | Bridging Continuous and Discrete Optimization Boot Camp 2017 | 2017-08-21 |
Part three shows an SOS/SDP proof that a triangle-free graph has at most asymptotically half the possible edges (an SOS version of Mantel’s theorem), by… | ||
| LP/SDP Hierarchies and Sum of Squares Proofs 4 | Bridging Continuous and Discrete Optimization Boot Camp 2017 | 2017-08-21 |
Presents a concrete SOS-based algorithm: a quasi-polynomial time N^{O(log N / ε^2)} method that approximates the max of a degree‑4 polynomial (M defined as… | ||
| Above Average-Case Analysis? | Learning, Algorithm Design and Beyond Worst-Case Analysis | 2016-11-14 |
Claims a polynomial-time procedure that, under an adversary who corrupts an ε fraction of samples (or distributions ε-close in total variation), recovers mean… | ||
| Planted Clique, Sum-of-Squares and Pseudo-Calibration | Random Instances and Phase Transitions (Simons Institute, 2016) | 2016-05-02 |
Shows that level-D Sum-of-Squares cannot rule out planted cliques much below √n: the integrality gap is ≥ n^{1/2 - O(√D / log n)} for D = o(log n), so any SOS… | ||
| Extended Formulations and Information Complexity | Information Theory in Complexity Theory and Combinatorics 2015 | 2015-04-24 |
Defines non-negative rank of the slack matrix and uses an entropy sampling reduction to show any factorization with R terms would let one sample a size-3^n… | ||
| Simple, Efficient and Neural Algorithms for Sparse Coding | Information Theory, Learning and Big Data (Simons Institute, 2015) | 2015-03-16 |
Proposes a simple online, local, Hebbian algorithm that decodes by multiplying by the current dictionary transpose and hard‑thresholding and then updates via… | ||
| A Polynomial Time Algorithm for Lossy Population Recovery | Semidefinite Optimization, Approximation and Applications 2014 | 2014-09-24 |
Proves a polynomial time algorithm for lossy population recovery for any fixed mu>0, showing recovery even when only ~1% of bits survive. Turns the problem… | ||
| nothing matches | ||