9 citations · 21 across the 14 of their papers we have counts for
15 papers
The anisotropic local law for sample covariance matrices under quadratic-form concentration
Renyuan Ma, Theodor Misiakiewicz
We study sample covariance matrices in the proportional regime . The columns $ \m…
Generalization, memorization, and overfitting for diffusion models trained in the lazy high-dimensional regime
Hugo Latourelle-Vigeant, Sinho Chewi, Aram-Alexandre Pooladian +2
Modern score-based generative models have achieved remarkable empirical success in high-dimensional tasks such as image, audio, and video synthesis. These models reduce distributio…
The sharp SAT/UNSAT phase transition in random ellipsoid fitting
Theodor Misiakiewicz, Garrett G. Wen
Let be independent standard Gaussian vectors in . An \emph{ellipsoid fit} is a matrix such that for every , so t…
Dynamical mean-field limit and replica-symmetric free energy for the orthogonally-invariant SK model
Zhou Fan, Theodor Misiakiewicz, Leda Wang +1
We study a class of diffusion processes on interacting through a symmetric matrix . When eigenvectors of are Haar-uniform on the orth…
Positive Distribution Shift as a Framework for Understanding Tractable Learning
Marko Medvedev, Idan Attias, Elisabetta Cornacchia +3
We study a setting where the goal is to learn a target function f(x) with respect to a target distribution D(x), but training is done on i.i.d. samples from a different training di…
Statistical-Computational Trade-offs in Learning Multi-Index Models via Harmonic Analysis
Hugo Latourelle-Vigeant, Theodor Misiakiewicz
We study the problem of learning multi-index models (MIMs), where the label depends on the input only through an unknown -dimensional…
When does Gaussian equivalence fail and how to fix it: Non-universal behavior of random features with quadratic scaling
Garrett G. Wen, Hong Hu, Yue M. Lu +2
A major effort in modern high-dimensional statistics has been devoted to the analysis of linear predictors trained on nonlinear feature embeddings via empirical risk minimization (…
Learning single-index models via harmonic decomposition
Nirmit Joshi, Hugo Koubbi, Theodor Misiakiewicz +1
We study the problem of learning single-index models, where the label depends on the input only through an unknown one-dimensio…
A Theory of Learning with Autoregressive Chain of Thought
Nirmit Joshi, Gal Vardi, Adam Block +4
For a given base class of sequence-to-next-token generators, we consider learning prompt-to-answer mappings obtained by iterating a fixed, time-invariant generator for multiple ste…
On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
Nirmit Joshi, Theodor Misiakiewicz, Nathan Srebro
The goal of this paper is to investigate the complexity of gradient algorithms when learning sparse functions (juntas). We introduce a type of Statistical Queries (),…
Dimension-free deterministic equivalents and scaling laws for random feature regression
Leonardo Defilippis, Bruno Loureiro, Theodor Misiakiewicz
In this work we investigate the generalization performance of random feature ridge regression (RFRR). Our main contribution is a general deterministic equivalent for the test error…
A non-asymptotic theory of Kernel Ridge Regression: deterministic equivalents, test error, and GCV estimator
Theodor Misiakiewicz, Basil Saeed
We consider learning an unknown target function using kernel ridge regression (KRR) given i.i.d. data , , where is a covariate vector and $y_i…
Asymptotics of Random Feature Regression Beyond the Linear Scaling Regime
Hong Hu, Yue M. Lu, Theodor Misiakiewicz
Recent advances in machine learning have been achieved by using overparametrized models trained until near interpolation of the training data. It was shown, e.g., through the doubl…
Spectrum of inner-product kernel matrices in the polynomial regime and multiple descent phenomenon in kernel ridge regression
Theodor Misiakiewicz
We study the spectrum of inner-product kernel matrices, i.e., matrices with entries where the $( \textbf{x}_i)_{i \l…
Efficient reconstruction of transmission probabilities in a spreading process from partial observations
Andrey Y. Lokhov, Theodor Misiakiewicz
An important problem of reconstruction of diffusion network and transmission probabilities from the data has attracted a considerable attention in the past several years. A number…