Statistical Learning
Clustering Redemption–Beyond the Impossibility of Kleinberg’s Axioms
Vincent Cohen-Addad, Varun Kanade, Frederik Mallmann-Trenn
Neural Information Processing Systems http://nips.cc/
Deep Neural Nets with Interpolating Function as Output Activation
Bao Wang, Xiyang Luo, Zhen Li, Wei Zhu, Zuoqiang Shi, Stanley Osher
And we propose end-to-end training and testing algorithms for this new architecture. Compared to classical neural nets with softmax function as output activation, the surrogate with interpolating function as output activation combines advantages of both deep and manifold learning.
Quadrature-based features for kernel approximation
Marina Munkhoeva, Yermek Kapushev, Evgeny Burnaev, Ivan Oseledets
We consider the problem of improving kernel approximation via randomized feature maps.
Multi-domain Causal Structure Learning in Linear Systems
AmirEmad Ghassami, Negar Kiyavash, Biwei Huang, Kun Zhang
Our approach unifies the idea in those works and generalizes to the case that there is no such invariance across the domains. Our proposed methods are generally capable of identifying causal direction from fewer than ten domains.
Coupled Variational Bayes via Optimization Embedding
Theoretically, we establish an interesting connection to gradient flow and demonstrate the extreme flexibility of this implicit distribution family in the limit sense.
On Controllable Sparse Alternatives to Softmax
Anirban Laha, Saneem Ahmed Chemmengath, Priyanka Agrawal, Mitesh Khapra, Karthik Sankaranarayanan, Harish G. Ramaswamy
Neural Information Processing Systems http://nips.cc/
Algorithmic Linearly Constrained Gaussian Processes
The resulting mean function is used for regression.
New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and Convexity
Pan Zhou, Xiaotong Yuan, Jiashi Feng
As an incremental-gradient algorithm, the hybrid stochastic gradient descent (HS-GD) enjoys merits of both stochastic and full gradient methods for finite-sum problem optimization.
A Bayes-Sard Cubature Method
Toni Karvonen, Chris J. Oates, Simo Sarkka
Neural Information Processing Systems http://nips.cc/
Representation Learning of Compositional Data
Marta Avalos, Richard Nock, Cheng Soon Ong, Julien Rouar, Ke Sun
We consider the problem of learning a low dimensional representation for compositional data.