Bayesian Learning
A Polynomial Time Algorithm for Log-Concave Maximum Likelihood via Locally Exponential Families
Brian Axelrod, Ilias Diakonikolas, Alistair Stewart, Anastasios Sidiropoulos, Gregory Valiant
Neural Information Processing Systems http://nips.cc/
This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization
Bayesian Optimization (BO) is an effective framework for black-box optimization.
Multi-value Rule Sets for Interpretable Classification with Feature-Efficient Representations
Neural Information Processing Systems http://nips.cc/
Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
When training deep neural networks, a model's generalization error is often observed to follow a power scaling law dependent both on the model size and the
Bayesian Control of Large MDPs with Unknown Dynamics in Data-Poor Environments
Mahdi Imani, Seyede Fatemeh Ghoreishi, Ulisses M. Braga-Neto
Neural Information Processing Systems http://nips.cc/
Gradient Information for Representation and Modeling
Jie Ding, Robert Calderbank, Vahid Tarokh
Neural Information Processing Systems http://nips.cc/
Model
We further show that optimistic posterior sampling can control this Hellinger distance, when we measure model error via data likelihood. This technique allows us to design and analyze unified posterior sampling algorithms with state-of-the-art sample complexity guarantees for many model-based RL settings.
Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates
Adil SALIM, Dmitry Koralev, Peter Richtarik
Neural Information Processing Systems http://nips.cc/
Toward Better PAC-Bayes Bounds for Uniformly Stable Algorithms Yunwen Lei 2
We give sharper bounds for uniformly stable randomized algorithms in a PAC-Bayesian framework, which improve the existing results by up to a factor of n (ignoring a log factor), where n is the sample size. The key idea is to bound the moment generating function of the generalization gap using concentration of weakly dependent random variables due to Bousquet et al (2020). We introduce an assumption of sub-exponential stability parameter, which allows a general treatment that we instantiate in two applications: stochastic gradient descent and randomized coordinate descent. Our results eliminate the requirement of strong convexity from previous results, and hold for non-smooth convex problems.