Technology
Natasha 2: Faster Non-Convex Optimization Than SGD
In diverse world of deep learning research has given rise to numerous architectures for neural networks(convolutionalones,longshorttermmemoryones,etc). However,tothisdate,theunderlying training algorithms for neural networks are still stochastic gradient descent (SGD) and its heuristic variants.
Scalable Deep Generative Relational Model with High-Order Node Dependence
Xuhui Fan, Bin Li, Caoyuan Li, Scott SIsson, Ling Chen
Neural Information Processing Systems http://nips.cc/
Random Projections with Asymmetric Quantization
Neural Information Processing Systems http://nips.cc/
Distributionally Robust Graphical Models
Rizal Fathony, Ashkan Rezaei, Mohammad Ali Bashiri, Xinhua Zhang, Brian Ziebart
Neural Information Processing Systems http://nips.cc/
ReFIR: GroundingLargeRestorationModels withRetrievalAugmentation
Recently, diffusion models [10, 11] have emerged as a promising alternative, delivering noteworthy results in real-world image restoration [12, 13, 14].
Demystifying excessively volatile human learning: A Bayesian persistent prior and a neural approximation
Chaitanya Ryali, Gautam Reddy, Angela J. Yu
Neural Information Processing Systems http://nips.cc/
Space and Time Efficient Kernel Density Estimation in High Dimensions
Arturs Backurs, Piotr Indyk, Tal Wagner
However, their data structure requires a significantly increased super-linear storage space, as well as super-linear preprocessing time. These limitations inhibit the practical applicability of their approach on large datasets.