Performance Analysis
Union of Intersections (UoI) for Interpretable Data Driven Discovery and Prediction
Kristofer Bouchard, Alejandro Bujan, Fred Roosta, Shashanka Ubaru, Mr. Prabhat, Antoine Snijders, Jian-Hua Mao, Edward Chang, Michael W. Mahoney, Sharmodeep Bhattacharya
We introduce Union of Intersections (UoI), a flexible, modular, and scalable framework for enhanced model selection and estimation.
Selective Classification for Deep Neural Networks
Neural Information Processing Systems http://nips.cc/
Equality of Opportunity in Supervised Learning
Moritz Hardt, Eric Price, Eric Price, Nati Srebro
We enourage readers to consult the more complete manuscript on the arXiv.
An Error Detection and Correction Framework for Connectomics
Jonathan Zung, Ignacio Tartavull, Kisuk Lee, H. Sebastian Seung
Both tasks take as input the raw image and a binary mask representing a candidate object.
Practical Locally Private Heavy Hitters
Raef Bassily, Kobbi Nissim, Uri Stemmer, Abhradeep Guha Thakurta
With a typically large number of participants in local algorithms ( n in the millions), this reduction in time complexity, in particular at the user side, is crucial for the use of such algorithms in practice. We implemented Algorithm TreeHist to verify our theoretical analysis and compared its performance with the performance of Google's RAPPOR code.
Reconstruct & Crush Network
Erinc Merdivan, Mohammad Reza Loghmani, Matthieu Geist
The resulting neural network thus learns to reconstruct data from the first distribution while crushing data from the second distribution.
Recycling Privileged Learning and Distribution Matching for Fairness
Novi Quadrianto, Viktoriia Sharmanska
Machine learning technologies have permeated everyday life and it is common nowadays that an automated system makes decisions for/about us, such as who is going to get bank credit.
Model-Powered Conditional Independence Test
We consider the problem of non-parametric Conditional Independence testing (CI testing) for continuous random variables. Given i.i.d samples from the joint distribution
Assessing Generative Models via Precision and Recall
Mehdi S. M. Sajjadi, Olivier Bachem, Mario Lucic, Olivier Bousquet, Sylvain Gelly
As aresult, surrogate metrics are often used to assess the quality of the trained models.
AdamNX: An Adam improvement algorithm based on a novel exponential decay mechanism for the second-order moment estimate
Zhu, Meng, Xiao, Quan, Min, Weidong
Since the 21st century, artificial intelligence has been leading a new round of industrial revolution. Under the training framework, the optimization algorithm aims to stably converge high-dimensional optimization to local and even global minima. Entering the era of large language models, although the scale of model parameters and data has increased, Adam remains the mainstream optimization algorithm. However, compared with stochastic gradient descent (SGD) based optimization algorithms, Adam is more likely to converge to non-flat minima. To address this issue, the AdamNX algorithm is proposed. Its core innovation lies in the proposition of a novel type of second-order moment estimation exponential decay rate, which gradually weakens the learning step correction strength as training progresses, and degrades to momentum SGD in the stable training period, thereby improving the stability of training in the stable period and possibly enhancing generalization ability. Experimental results show that our second-order moment estimation exponential decay rate is better than the current second-order moment estimation exponential decay rate, and AdamNX can stably outperform Adam and its variants in terms of performance. Our code is open-sourced at https://github.com/mengzhu0308/AdamNX.