Europe
Private Stochastic Convex Optimization with Optimal Rates
Raef Bassily, Vitaly Feldman, Kunal Talwar, Abhradeep Guha Thakurta
Neural Information Processing Systems http://nips.cc/
NeuralBellman-FordNetworks: AGeneralGraph NeuralNetworkFrameworkforLinkPrediction
Link prediction is a very fundamental task on graphs.
Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
These limitations, both theoretical and practical, underscore the need for novel sketching algorithms.
Convergence-Rate-Matching Discretization of Accelerated Optimization Flows Through Opportunistic State-Triggered Control
Neural Information Processing Systems http://nips.cc/
Multi Time Scale World Models
Inference in the introduced linear Gaussian SSM is straightforward and can be performed using Kalman prediction and observation updates.
f6185f0ef02dcaec414a3171cd01c697-Paper.pdf
Consider the problem of training deep neural networks on large annotated datasets, such as ImageNet [1]. This problem can be formalized as finding optimal parameters for a given neural networka,parameterized byw,w.r.t.