Follow
hadi daneshmand
hadi daneshmand
Postdoctoral Associate, MIT
Verified email at mit.edu - Homepage
Title
Cited by
Cited by
Year
Inferring causal molecular networks: empirical assessment through a community-based effort
SM Hill, LM Heiser, T Cokelaer, M Unger, NK Nesser, DE Carlin, Y Zhang, ...
Nature methods 13 (4), 310-318, 2016
2362016
Escaping saddles with stochastic gradients
H Daneshmand, J Kohler, A Lucchi, T Hofmann
International Conference on Machine Learning, 1155-1164, 2018
1562018
Estimating diffusion network structures: Recovery conditions, sample complexity & soft-thresholding algorithm
H Daneshmand, M Gomez-Rodriguez, L Song, B Schoelkopf
International conference on machine learning, 793-801, 2014
1402014
Exponential convergence rates for batch normalization: The power of length-direction decoupling in non-convex optimization
J Kohler, H Daneshmand, A Lucchi, T Hofmann, M Zhou, K Neymeyr
The 22nd International Conference on Artificial Intelligence and Statistics …, 2019
133*2019
Local saddle point optimization: A curvature exploitation approach
L Adolphs, H Daneshmand, A Lucchi, T Hofmann
The 22nd International Conference on Artificial Intelligence and Statistics …, 2019
1212019
Batch normalization provably avoids ranks collapse for randomly initialised deep networks
H Daneshmand, J Kohler, F Bach, T Hofmann, A Lucchi
Advances in Neural Information Processing Systems 33, 18387-18398, 2020
51*2020
Adaptive newton method for empirical risk minimization to statistical accuracy
A Mokhtari, H Daneshmand, A Lucchi, T Hofmann, A Ribeiro
Advances in Neural Information Processing Systems 29, 2016
512016
Starting small-learning with adaptive sample sizes
H Daneshmand, A Lucchi, T Hofmann
International conference on machine learning, 1463-1471, 2016
502016
Estimating diffusion networks: Recovery conditions, sample complexity & soft-thresholding algorithm
M Gomez-Rodriguez, L Song, H Daneshmand, B Schölkopf
The Journal of Machine Learning Research 17 (1), 3092-3120, 2016
42*2016
Transformers learn to implement preconditioned gradient descent for in-context learning
K Ahn, X Cheng, H Daneshmand, S Sra
Advances in Neural Information Processing Systems 36, 2024
362024
Batch normalization orthogonalizes representations in deep random networks
H Daneshmand, A Joudaki, F Bach
Advances in Neural Information Processing Systems 34, 4896-4906, 2021
262021
A time-aware recommender system based on dependency network of items
SM Daneshmand, A Javari, SE Abtahi, M Jalili
The Computer Journal 58 (9), 1955-1966, 2015
242015
Revisiting the role of euler numerical integration on acceleration and stability in convex optimization
P Zhang, A Orvieto, H Daneshmand, T Hofmann, RS Smith
International Conference on Artificial Intelligence and Statistics, 3979-3987, 2021
82021
On the impact of activation and normalization in obtaining isometric embeddings at initialization
A Joudaki, H Daneshmand, F Bach
Advances in Neural Information Processing Systems 36, 2024
42024
Rethinking the Variational Interpretation of Accelerated Optimization Methods
P Zhang, A Orvieto, H Daneshmand
Advances in Neural Information Processing Systems 34, 14396-14406, 2021
4*2021
Efficient displacement convex optimization with particle gradient descent
H Daneshmand, JD Lee, C Jin
arXiv preprint arXiv:2302.04753, 2023
32023
On Bridging the Gap between Mean Field and Finite Width Deep Random Multilayer Perceptron with Batch Normalization
A Joudaki, H Daneshmand, F Bach
22023
Polynomial-time sparse measure recovery
H Daneshmand, F Bach
arXiv preprint arXiv:2204.07879, 2022
22022
Towards training without depth limits: Batch normalization without gradient explosion
A Meterez, A Joudaki, F Orabona, A Immer, G Rätsch, H Daneshmand
arXiv preprint arXiv:2310.02012, 2023
12023
Optimization for Neural Networks: Quest for Theoretical Understandings
H Daneshmand
ETH Zurich, 2020
12020
The system can't perform the operation now. Try again later.
Articles 1–20