Technology
Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classification
Harsh Shrivastava, Eugene Bart, Bob Price, Hanjun Dai, Bo Dai, Srinivas Aluru
Neural Information Processing Systems http://nips.cc/
SparseHigh-DimensionalIsotonicRegression
We consider the problem of estimating an unknown coordinate-wise monotone function given noisy measurements, known as the isotonic regression problem. Often, only a small subset of the features affects the output.
High-Fidelity Audio Compression with Improved RVQGAN
Language models have been successfully used to model natural signals, such as images, speech, and music.
Learning from Label Proportions with Generative Adversarial Networks
Jiabin Liu, Bo Wang, Zhiquan Qi, YingJie Tian, Yong Shi
Neural Information Processing Systems http://nips.cc/
Learning sparse neural networks via sensitivity-driven regularization
Enzo Tartaglione, Skjalg Lepsøy, Attilio Fiandrotti, Gianluca Francini
Neural Information Processing Systems http://nips.cc/
d4c2f25bf0c33065b7d4fb9be2a9add1-Paper-Conference.pdf
We call this distinction thediscrimination risk. We prove that a higher discrimination risk can amplify the unfairness of a machine learning model applied totheimputed data.
Coarse-to-FineVision-LanguagePre-trainingwith FusionintheBackbone
Vision-language (VL) pre-training has recently received considerable attention.
Critical initialisation for deep signal propagation in noisy rectifier neural networks
Arnu Pretorius, Elan van Biljon, Steve Kroon, Herman Kamper
Neural Information Processing Systems http://nips.cc/