Europe
Achieving Domain-Independent Certified Robustness via Knowledge Continuity Alan Sun
These bounds are independent of domain modality, norms, and distribution.
Online Learning via the Differential Privacy Lens
Jacob D. Abernethy, Young Hun Jung, Chansoo Lee, Audra McMillan, Ambuj Tewari
Neural Information Processing Systems http://nips.cc/
Geometric Algebra Transformer
Such data can take numerous forms, for instance points, direction vectors, translations, or rotations, but to date there is no single architecture that can be applied to such a wide variety of geometric types while respecting their symmetries. In this paper we introduce the Geometric Algebra Transformer (GA Tr), a general-purpose architecture for geometric data.
Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction
Difan Zou, Pan Xu, Quanquan Gu
Figure 3: Ex represents (c)-(d) ConB.
Doubly Robust Bayesian Inference for Non-Stationary Streaming Data with $\beta$-Divergences
Jeremias Knoblauch, Jack E. Jewson, Theodoros Damoulas
Neural Information Processing Systems http://nips.cc/
Fisher Efficient Inference of Intractable Models
Song Liu, Takafumi Kanamori, Wittawat Jitkrittum, Yu Chen
We prove its consistency and show that the asymptotic variance ofitssolution canattaintheequality oftheefficiencybound undermild regularity conditions.
Meta-Learning Adversarial Bandit Algorithms
Such feedback can be stochastic, e.g. the
Alleviating Label Switching with Optimal Transport
Pierre Monteiller, Sebastian Claici, Edward Chien, Farzaneh Mirzazadeh, Justin M. Solomon, Mikhail Yurochkin
Sampling and inference algorithms behave poorly as the number of modes increases, andthisproblem isonlyexacerbated inthiscontextsinceincreasing thenumber ofcomponents in the mixture model leads to a super-exponential increase in the number of modes of the posterior.