Statistical Learning
Data-dependent PAC-Bayes priors via differential privacy
Gintare Karolina Dziugaite, Daniel M. Roy
Neural Information Processing Systems http://nips.cc/
How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD
However, in terms of making the gradients small, the original SGD does not give an optimal rate, even when f(x) is convex. If f(x) is convex, to find a point with gradient norm ε, we design an algorithm SGD3withanear-optimalrate eO(ε 2),improvingthebestknownrateO(ε 8/3) of [17].
Integrating Bayesian and Discriminative Sparse Kernel Machines for Multi-class Active Learning
Neural Information Processing Systems http://nips.cc/
Linear Transformers are Versatile In-Context Learners
The transformer architecture (V aswani et al., 2017) has revolutionized the field of machine learning,
L4: Practical loss-based stepsize adaptation for deep learning
Neural Information Processing Systems http://nips.cc/
6e2986deda273d8fb903342841fcc4dc-Paper-Conference.pdf
These kinds of attacks are known as poisoning attacks .
Variance Reduction in Bipartite Experiments through Correlation Clustering
Jean Pouget-Abadie, Kevin Aydin, Warren Schudy, Kay Brodersen, Vahab Mirrokni
Neural Information Processing Systems http://nips.cc/