Show newer

"Playing the whole game": A data collection and analysis exercise with Google Calendar. (arXiv:2002.11767v1 [stat.OT]) arxiv.org/abs/2002.11767

Rethinking the Hyperparameters for Fine-tuning. (arXiv:2002.11770v1 [cs.CV]) arxiv.org/abs/2002.11770

Moniqua: Modulo Quantized Communication in Decentralized SGD. (arXiv:2002.11787v1 [cs.LG]) arxiv.org/abs/2002.11787

PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models. (arXiv:2002.11791v1 [cs.LG]) arxiv.org/abs/2002.11791

Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization. (arXiv:2002.11798v1 [cs.LG]) arxiv.org/abs/2002.11798

Disentangling Adaptive Gradient Methods from Learning Rates. (arXiv:2002.11803v1 [cs.LG]) arxiv.org/abs/2002.11803

Memory-Constrained No-Regret Learning in Adversarial Bandits. (arXiv:2002.11804v1 [cs.LG]) arxiv.org/abs/2002.11804

An Information Diffusion Approach to Rumor Propagation and Identification on Twitter. (arXiv:2002.11104v1 [cs.SI]) arxiv.org/abs/2002.11104

Dynamic Incentive-aware Learning: Robust Pricing in Contextual Auctions. (arXiv:2002.11137v1 [cs.LG]) arxiv.org/abs/2002.11137

TxSim:Modeling Training of Deep Neural Networks on Resistive Crossbar Systems. (arXiv:2002.11151v1 [cs.LG]) arxiv.org/abs/2002.11151

Fundamental Issues Regarding Uncertainties in Artificial Neural Networks. (arXiv:2002.11152v1 [stat.ML]) arxiv.org/abs/2002.11152

Smoothing Graphons for Modelling Exchangeable Relational Data. (arXiv:2002.11159v1 [stat.ML]) arxiv.org/abs/2002.11159

Data-driven super-parameterization using deep learning: Experimentation with multi-scale Lorenz 96 systems and transfer-learning. (arXiv:2002.11167v1 [physics.ao-ph]) arxiv.org/abs/2002.11167

A Sample Complexity Separation between Non-Convex and Convex Meta-Learning. (arXiv:2002.11172v1 [cs.LG]) arxiv.org/abs/2002.11172

Information Directed Sampling for Linear Partial Monitoring. (arXiv:2002.11182v1 [stat.ML]) arxiv.org/abs/2002.11182

Reliable Estimation of Kullback-Leibler Divergence by Controlling Discriminator Complexity in the Reproducing Kernel Hilbert Space. (arXiv:2002.11187v1 [cs.LG]) arxiv.org/abs/2002.11187

QEML (Quantum Enhanced Machine Learning): Using Quantum Computing to Enhance ML Classifiers and Feature Spaces. (arXiv:2002.10453v1 [quant-ph]) arxiv.org/abs/2002.10453

Precise Tradeoffs in Adversarial Training for Linear Regression. (arXiv:2002.10477v1 [cs.LG]) arxiv.org/abs/2002.10477

Interpolating Between Gradient Descent and Exponentiated Gradient Using Reparameterized Gradient Descent. (arXiv:2002.10487v1 [cs.LG]) arxiv.org/abs/2002.10487

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.