Country
Lipschitz regularity of deep neural networks: analysis and efficient estimation
Deep neural networks are notorious for being sensitive to small well-chosen perturbations, and estimating the regularity of such architectures is of utmost importance for safe and robust practical applications. In this paper, we investigate one of the key characteristics to assess the regularity of such methods: the Lipschitz constant of deep learning architectures.
Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning
Harsh Gupta, R. Srikant, Lei Ying
Neural Information Processing Systems http://nips.cc/
Anton V oronov MIPT, Yandex Mikhail Khoroshikh
One emerging area of research is the fast adaptation of large text-to-image models to smaller datasets or new visual concepts.
Rates of Convergence for Large-scale Nearest Neighbor Classification
Xingye Qiao, Jiexin Duan, Guang Cheng
Inadditiontothememory limitation, there are other important concerns.
NEON2: Finding Local Minima via First-Order Oracles
It works both in the stochastic and the deterministic settings, without hurting the algorithm'sperformance. As applications, our reduction turns Natasha2 into a first-order method without hurting its theoretical performance. It also converts SGD, GD, SCSG, and SVRG into algorithms finding approximate local minima, outperforming some bestknownresults.
Learning Invariances using the Marginal Likelihood
Mark van der Wilk, Matthias Bauer, ST John, James Hensman
Neural Information Processing Systems http://nips.cc/
Surfing: Iterative Optimization Over Incrementally Trained Deep Networks
Ganlin Song, Zhou Fan, John Lafferty
We investigate a sequential optimization procedure to minimize the empiricalrisk functional fbθ(x) = 12kGbθ(x) yk2 for certain families of deep networks Gθ(x).
A V-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis Susan Liang 1 Chao Huang
This consistency ensures perceptual realism and immersion, enriching the overall user experience.