Theodor Misiakiewicz

Computer Science · Physical Sciences

11h-index438citations40works0.52yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Stochastic Gradient Optimization Techniques(12), Neural Networks and Applications(11), Machine Learning and Algorithms(11), Model Reduction and Neural Networks(9), Face and Expression Recognition(4)

Publications40 total

Statistical-Computational Trade-offs in Learning Multi-Index Models via Harmonic Analysis
arXiv (Cornell University)·2026Open Access
Statistical-Computational Trade-offs in Learning Multi-Index Models via Harmonic Analysis
arXiv (Cornell University)·2026Open Access
Positive Distribution Shift as a Framework for Understanding Tractable Learning
arXiv (Cornell University)·2026Open Access
Positive Distribution Shift as a Framework for Understanding Tractable Learning
ArXiv.org·2026Open Access
Universal and non-universal behavior in Empirical Risk Minimization
Open Collections·2026Open Access
When does Gaussian equivalence fail and how to fix it: Non-universal behavior of random features with quadratic scaling
arXiv (Cornell University)·2025Open Access
Learning single-index models via harmonic decomposition
arXiv (Cornell University)·2025Open Access
An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds
ArXiv.org·2025Open Access
A Theory of Learning with Autoregressive Chain of Thought
arXiv (Cornell University)·2025Open Access
Sparse PCA: Phase Transitions in the Critical Regime
arXiv (Cornell University)·2024Open Access
Six lectures on linearized neural networks
Journal of Statistical Mechanics Theory and Experiment·2024· 4 cited
On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
arXiv (Cornell University)·2024Open Access
Dimension-free deterministic equivalents and scaling laws for random feature regression
arXiv (Cornell University)·2024· 2 citedOpen Access
A non-asymptotic theory of Kernel Ridge Regression: deterministic equivalents, test error, and GCV estimator
arXiv (Cornell University)·2024· 1 citedOpen Access
Asymptotics of Random Feature Regression Beyond the Linear Scaling Regime
arXiv (Cornell University)·2024· 2 citedOpen Access
On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
2024
Dimension-free deterministic equivalents and scaling laws for random feature regression
2024
Precise learning curves and higher-order scaling limits for dot-product kernel regression <sup>*</sup>
Journal of Statistical Mechanics Theory and Experiment·2023· 4 citedOpen Access
Six Lectures on Linearized Neural Networks
arXiv (Cornell University)·2023· 2 citedOpen Access
SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics
arXiv (Cornell University)·2023· 3 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Andrea Montanari(16), Mei Song(13), Behrooz Ghorbani(5), Nirmit Joshi(4), Nathan Srebro(4), Yue M. Lu(3), Roberto I. Oliveira(2), Emmanuel Abbé(2), Enric Boix-Adserà(2), Hong Hu(2), Leonardo Defilippis(2), Bruno Loureiro(2), Marc Vuffray(2), Marko Medvedev(2), Idan Attias(2), Elisabetta Cornacchia(2), Gal Vardi(2), Zhaoran Wang(2), Hugo Latourelle-Vigeant(2), Mei Song(1)