Danil Akhtiamov

According to our database, Danil Akhtiamov authored at least 15 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Precise Performance of Linear Denoisers in the Proportional Regime.

Reza Ghane, Danil Akhtiamov, Babak Hassibi

CoRR, March, 2026

Dual Space Preconditioning for Gradient Descent in the Overparameterized Regime.

Reza Ghane, Danil Akhtiamov, Babak Hassibi

CoRR, March, 2026

Implicit Bias and Convergence of Matrix Stochastic Mirror Descent.

Danil Akhtiamov, Reza Ghane, Omead Pooladzandi, Babak Hassibi

CoRR, February, 2026

Gaussian Universality for Diffusion Models.

Reza Ghane, Anthony Bao, Danil Akhtiamov, Babak Hassibi

IEEE Signal Process. Lett., 2026

2025

A Novel Gaussian Min-Max Theorem and Its Applications.

Danil Akhtiamov, David Bosch, Reza Ghane, Kanumuri Nithin Varma, Babak Hassibi

IEEE Trans. Inf. Theory, November, 2025

One-Bit Quantization for Random Features Models.

Danil Akhtiamov, Reza Ghane, Babak Hassibi

CoRR, October, 2025

A Precise Performance Analysis of the Randomized Singular Value Decomposition.

Danil Akhtiamov, Reza Ghane, Babak Hassibi

CoRR, October, 2025

Concentration of Measure for Distributions Generated via Diffusion Models.

Reza Ghane, Anthony Bao, Danil Akhtiamov, Babak Hassibi

CoRR, January, 2025

One-Bit Quantization and Sparsification for Multiclass Linear Classification With Strong Regularization.

Reza Ghane, Danil Akhtiamov, Babak Hassibi

IEEE Trans. Signal Process., 2025

2024

One-Bit Quantization and Sparsification for Multiclass Linear Classification via Regularized Regression.

Reza Ghane, Danil Akhtiamov, Babak Hassibi

CoRR, 2024

Universality in Transfer Learning for Linear Models.

Reza Ghane, Danil Akhtiamov, Babak Hassibi

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Regularized Linear Regression for Binary Classification.

Danil Akhtiamov, Reza Ghane, Babak Hassibi

Proceedings of the IEEE International Symposium on Information Theory, 2024

2023

The Generalization Error of Stochastic Mirror Descent on Over-Parametrized Linear Models.

Danil Akhtiamov, Babak Hassibi

CoRR, 2023

2022

Connectedness of loss landscapes via the lens of Morse theory.

Danil Akhtiamov, Matt Thomson

Proceedings of the NeurIPS Workshop on Symmetry and Geometry in Neural Representations, 2022

2021

Maximums of the Additive Differential Probability of Exclusive-Or.

Nicky Mouha, Nikolay Kolomeec, Danil Akhtiamov, Ivan Sutormin, Matvey Panferov, Kseniya Titova, Tatiana Bonich, Evgeniya Ishchukova, Natalia N. Tokareva, Bulat Zhantulikov

IACR Trans. Symmetric Cryptol., 2021