Original title: Unsupervised Multimodal Surface Registration with Geometric Deep Learning Authors: Mohamed A. Suliman, Logan Z. J. Williams, Abdulah Fawaz, Emma C. Robinson The article presents GeoMorph, a new geometric deep-learning system for registering cortical…
Read more of Can Geometric Deep Learning Register Surfaces Across Modes Without Supervision?
Original title: Adaptive Sampling for Deep Learning via Efficient Nonparametric Proxies Authors: Shabnam Daghaghi, Benjamin Coleman, Benito Geordie, Anshumali Shrivastava In this article, the focus is on enhancing neural network training speed through data sampling.…
Read more of How Can Deep Learning Benefit from Adaptive Sampling and Nonparametric Proxies?
Original title: Differentially Private Non-Convex Optimization under the KL Condition with Optimal Rates Authors: Michael Menart, Enayat Ullah, Raman Arora, Raef Bassily, Cristóbal Guzmán The article tackles private empirical risk minimization (ERM) problems considering the…
Original title: ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization Authors: Prateek Yadav, Leshem Choshen, Colin Raffel, Mohit Bansal In the world of refining language models, Parameter-efficient fine-tuning (PEFT) techniques enable tailored…
Read more of Can ComPEFT Improve Efficiency with Parameter Updates?
Original title: Curriculum Learning and Imitation Learning for Model-free Control on Financial Time-series Authors: Woosung Koh, Insu Choi, Yuntae Jang, Gimin Kang, Woo Chang Kim This article delves into the application of curriculum learning and…
Original title: Ball Mill Fault Prediction Based on Deep Convolutional Auto-Encoding Network Authors: Xinkun Ai, Kun Liu, Wei Zheng, Yonggang Fan, Xinwu Wu, Peilong Zhang, LiYe Wang, JanFeng Zhu, Yuan Pan The article focuses on…
Read more of Can Deep Convolutional Auto-Encoding Networks Predict Ball Mill Faults?
Original title: Predict-Then-Optimize by Proxy: Learning Joint Models of Prediction and Optimization Authors: James Kotary, Vincenzo Di Vito, Jacob Christopher, Pascal Van Hentenryck, Ferdinando Fioretto The article explores decision-making processes modeled by optimization problems with…
Read more of Can Joint Prediction and Optimization be Learned by Proxy?
Original title: From Images to Connections: Can DQN with GNNs learn the Strategic Game of Hex? Authors: Yannik Keller, Jannis Blüml, Gopika Sudhakaran, Kristian Kersting The article examines strategic board games like Hex, known for…
Read more of Can DQN and GNNs Master Hex Strategy from Images to Connections?
Original title: DMLR: Data-centric Machine Learning Research — Past, Present and Future Authors: Luis Oala, Manil Maskey, Lilith Bat-Leah, Alicia Parrish, Nezihe Merve Gürel, Tzu-Sheng Kuo, Yang Liu, Rotem Dror, Danilo Brajovic, Xiaozhe Yao, Max…
Read more of Is DMLR Shaping the Past, Present, and Future of Machine Learning Research?
Original title: Explaining high-dimensional text classifiers Authors: Odelia Melamed, Rich Caruana In recent years, explainability has gained significance in unraveling AI-driven decisions. Yet, traditional methods face limitations when handling high-dimensional inputs and neural network classifiers.…
Read more of Can High-Dimensional Text Classifiers Be Explained?
