Statistical Learning
Single-Model Uncertainties for Deep Learning
Natasa Tagasovska, David Lopez-Paz
These certificates map out-of-distribution examples tonon-zero values, signaling epistemic uncertainty.
Greedy Sampling for Approximate Clustering in the Presence of Outliers
Aditya Bhaskara, Sharvaree Vadgama, Hong Xu
Neural Information Processing Systems http://nips.cc/
DistributionallyRobustOptimizationviaBallOracle Acceleration
In particular, we consider group-structured and boundedfdivergence uncertainty sets. Our approach relies on an accelerated method that queries a ball optimization oracle, i.e., a subroutine that minimizes the objective within a small ball around the query point. Our main contribution is efficient implementations of this oracle for DRO objectives.
Causal Inference and Mechanism Clustering of A Mixture of Additive Noise Models
Shoubo Hu, Zhitang Chen, Vahid Partovi Nia, Laiwan CHAN, Yanhui Geng
Obviously in ANM-MM, all observations are generated by a set of g.m.s, which share the same functionform(f)butdifferinparametervalues(ฮธ).
Wasserstein Distributionally Robust Optimization Through the Lens of Structural Causal Models and Individual Fairness
To address this gap, we first formulate the DRO problem from causality and individual fairness perspectives.
ATOMO: Communication-efficient Learning via Atomic Sparsification
Hongyi Wang, Scott Sievert, Shengchao Liu, Zachary Charles, Dimitris Papailiopoulos, Stephen Wright
Neural Information Processing Systems http://nips.cc/
The promises and pitfalls of Stochastic Gradient Langevin Dynamics
Nicolas Brosse, Alain Durmus, Eric Moulines
Neural Information Processing Systems http://nips.cc/
Gradient Sparsification for Communication-Efficient Distributed Optimization
Jianqiao Wangni, Jialei Wang, Ji Liu, Tong Zhang
In the synchronous stochastic gradient method, each worker processes a random minibatch of its training data, and then the local updates are synchronized by making anAll-Reduce step, which aggregates stochastic gradients from all workers, and taking aBroadcast step that transmits the updated parameter vector back toallworkers.