no code implementations • 25 Nov 2023 • David Lyver, Mihai Nica, Corentin Cot, Giacomo Cacciapaglia, Zahra Mohammadi, Edward W. Thommes, Monica-Gabriela Cojocaru
The epidemiology of pandemics is classically viewed using geographical and political borders; however, these artificial divisions can result in a misunderstanding of the current epidemiological state within a given region.
no code implementations • 31 Oct 2023 • Michal Lisicki, Mihai Nica, Graham W. Taylor
We introduce a novel approach for batch selection in Stochastic Gradient Descent (SGD) training, leveraging combinatorial bandit algorithms.
no code implementations • 18 Oct 2023 • Mufan Bill Li, Mihai Nica
Secondly, for an unshaped MLP at initialization, we derive the first order asymptotic correction to the layerwise correlation.
no code implementations • 5 Sep 2023 • Griffin Floto, Thorsteinn Jonsson, Mihai Nica, Scott Sanner, Eric Zhengyu Zhu
However, the desired continuous nature of the noising process can be at odds with discrete data.
no code implementations • 2 Jun 2023 • Cameron Jakub, Mihai Nica
We observe this degeneracy in the sense that on initialization, inputs tend to become more and more correlated as they travel through the layers of the network.
1 code implementation • 3 May 2023 • Mike Lasby, Anna Golubeva, Utku Evci, Mihai Nica, Yani Ioannou
Dynamic Sparse Training (DST) methods achieve state-of-the-art results in sparse neural network training, matching the generalization of dense models while enabling sparse training and inference.
no code implementations • 20 Feb 2023 • Cameron Jakub, Mihai Nica
In this paper, we examine the evolution of the angle between two inputs to a ReLU neural network as a function of the number of layers.
no code implementations • 19 Jul 2022 • Angus Galloway, Anna Golubeva, Mahmoud Salem, Mihai Nica, Yani Ioannou, Graham W. Taylor
Estimating the Generalization Error (GE) of Deep Neural Networks (DNNs) is an important task that often relies on availability of held-out data.
no code implementations • 6 Jun 2022 • Mufan Bill Li, Mihai Nica, Daniel M. Roy
In this work, we study the distribution of this random matrix.
1 code implementation • 30 Nov 2021 • Griffin Floto, Stefan Kremer, Mihai Nica
An important property for deep neural networks is the ability to perform robust out-of-distribution detection on previously unseen data.
no code implementations • 16 Oct 2021 • Xinhai Zhang, Jianbo Tao, Kaige Tan, Martin Törngren, José Manuel Gaspar Sánchez, Muhammad Rusyadi Ramli, Xin Tao, Magnus Gyllenhammar, Franz Wotawa, Naveen Mohan, Mihai Nica, Hermann Felbinger
The main contributions are: (i) introducing a comprehensive taxonomy for critical scenario identification methods; (ii) giving an overview of the state-of-the-art research based on the taxonomy encompassing 86 papers between 2017 and 2020; and (iii) identifying open issues and directions for further research.
no code implementations • NeurIPS 2021 • Mufan Bill Li, Mihai Nica, Daniel M. Roy
To provide a better approximation, we study ReLU ResNets in the infinite-depth-and-width limit, where both depth and width tend to infinity as their ratio, $d/n$, remains constant.
no code implementations • 17 Jan 2020 • Jihun Han, Mihai Nica, Adam R Stinchcombe
We introduce a deep neural network based method for solving a class of elliptic partial differential equations.
no code implementations • ICLR 2020 • Boris Hanin, Mihai Nica
Moreover, we prove that for such deep and wide networks, the NTK has a non-trivial evolution during training by showing that the mean of its first SGD update is also exponential in the ratio of network depth to width.
no code implementations • 14 Dec 2018 • Boris Hanin, Mihai Nica
The fluctuations we find can be thought of as a finite temperature correction to the limit in which first the size and then the number of matrices tend to infinity.
no code implementations • 15 Nov 2017 • Gerard Ben Arous, Song Mei, Andrea Montanari, Mihai Nica
We compute the expected number of critical points and local maxima of this objective function and show that it is exponential in the dimensions $n$, and give exact formulas for the exponential growth rate.
1 code implementation • 8 Sep 2015 • Mihai Nica
Instead, the optimal strategy for the player who trails is to make certain bold plays in an attempt catch up.
Probability Computer Science and Game Theory Optimization and Control 91A15, 60G40, 62L15, 91A60