Technology
The promises and pitfalls of Stochastic Gradient Langevin Dynamics
Nicolas Brosse, Alain Durmus, Eric Moulines
Neural Information Processing Systems http://nips.cc/
Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits
Neural Information Processing Systems http://nips.cc/
Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization
That is, to minimize simple regret. However, this objective remains understudied.
Information Competing Process for Learning Diversified Representations
Jie Hu, Rongrong Ji, ShengChuan Zhang, Xiaoshuai Sun, Qixiang Ye, Chia-Wen Lin, Qi Tian
Despitetheexciting progresses, learningdiversified representations remains as an open problem.
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.