Deep Learning Through the Lens of Example Difficulty

17 June 2021

Hartmut Maennel

Papers citing "Deep Learning Through the Lens of Example Difficulty"

50 / 112 papers shown

Title
Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning Nikhil Vyas Depen Morwani Rosie Zhao Gal Kaplun Sham Kakade Boaz Barak MLT 13 4 0 14 Jun 2023
Learning Causal Mechanisms through Orthogonal Neural Networks Peyman Sheikholharam Mashhadi Sławomir Nowaczyk CML DRL 23 0 0 05 Jun 2023
Adaptive Conformal Regression with Jackknife+ Rescaled Scores N. Deutschmann Mattia Rigotti María Rodríguez Martínez 23 10 0 31 May 2023
Parameter-Efficient Language Model Tuning with Active Learning in Low-Resource Settings Josip Jukić Jan vSnajder 23 4 0 23 May 2023
Incentivising the federation: gradient-based metrics for data selection and valuation in private decentralised training Dmitrii Usynin Daniel Rueckert Georgios Kaissis FedML 20 2 0 04 May 2023
Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures Eugenia Iofinova Alexandra Peste Dan Alistarh 23 9 0 25 Apr 2023
Learning Sample Difficulty from Pre-trained Models for Reliable Prediction Peng Cui Dan Zhang Zhijie Deng Yinpeng Dong Junyi Zhu 16 12 0 20 Apr 2023
Simulated Annealing in Early Layers Leads to Better Generalization Amirm. Sarfi Zahra Karimpour Muawiz Chaudhary N. Khalid Mirco Ravanelli Sudhir Mudur Eugene Belilovsky AI4CE CLL 14 7 0 10 Apr 2023
On the Variance of Neural Network Training with respect to Test Sets and Distributions Keller Jordan OOD 16 10 0 04 Apr 2023
A Bag-of-Prototypes Representation for Dataset-Level Applications Wei-Chih Tu Weijian Deng Tom Gedeon Liang Zheng 38 9 0 23 Mar 2023
Eliciting Latent Predictions from Transformers with the Tuned Lens Nora Belrose Zach Furman Logan Smith Danny Halawi Igor V. Ostrovsky Lev McKinney Stella Biderman Jacob Steinhardt 22 192 0 14 Mar 2023
When does Privileged Information Explain Away Label Noise? Guillermo Ortiz-Jiménez Mark Collier Anant Nawalgaria Alexander DÁmour Jesse Berent Rodolphe Jenatton E. Kokiopoulou NoLa 154 7 0 03 Mar 2023
Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics Nihal Murali A. Puli Ke Yu Rajesh Ranganath Kayhan Batmanghelich AAML 40 8 0 18 Feb 2023
Task-Aware Information Routing from Common Representation Space in Lifelong Learning Prashant Bhat Bahram Zonooz Elahe Arani CLL 18 24 0 14 Feb 2023
How to prepare your task head for finetuning Yi Ren Shangmin Guo Wonho Bae Danica J. Sutherland 9 14 0 11 Feb 2023
Blockwise Self-Supervised Learning at Scale Shoaib Ahmed Siddiqui David M. Krueger Yann LeCun Stéphane Deny SSL 25 15 0 03 Feb 2023
Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications Chengyu Dong OOD UQCV BDL AI4CE 26 0 0 02 Feb 2023
Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation Weijian Deng Yumin Suh Stephen Gould Liang Zheng UQCV 26 12 0 02 Feb 2023
Data Valuation Without Training of a Model Nohyun Ki Hoyong Choi Hye Won Chung TDI 16 31 0 03 Jan 2023
Smooth Sailing: Improving Active Learning for Pre-trained Language Models with Representation Smoothness Analysis Josip Jukić Jan Snajder 11 5 0 20 Dec 2022
Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features Qingrui Jia Xuhong Li Lei Yu Jiang Bian Penghao Zhao Shupeng Li Haoyi Xiong Dejing Dou NoLa 22 5 0 19 Dec 2022
Leveraging Unlabeled Data to Track Memorization Mahsa Forouzesh Hanie Sedghi Patrick Thiran NoLa TDI 30 3 0 08 Dec 2022
CrossSplit: Mitigating Label Noise Memorization through Data Splitting Jihye Kim A. Baratin Yan Zhang Simon Lacoste-Julien NoLa 18 7 0 03 Dec 2022
Layer-Stack Temperature Scaling Amr Khalifa Michael C. Mozer Hanie Sedghi Behnam Neyshabur Ibrahim M. Alabdulmohsin 75 2 0 18 Nov 2022
Characterizing Datapoints via Second-Split Forgetting Pratyush Maini Saurabh Garg Zachary Chase Lipton J. Zico Kolter 23 34 0 26 Oct 2022
The Dynamic of Consensus in Deep Networks and the Identification of Noisy Labels Daniel Shwartz Uri Stern D. Weinshall NoLa 33 2 0 02 Oct 2022
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics Shoaib Ahmed Siddiqui Nitarshan Rajkumar Tegan Maharaj David M. Krueger Sara Hooker 37 27 0 20 Sep 2022
Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty Thomas George Guillaume Lajoie A. Baratin 23 5 0 19 Sep 2022
Efficient Methods for Natural Language Processing: A Survey Marcos Vinícius Treviso Ji-Ung Lee Tianchu Ji Betty van Aken Qingqing Cao ... Emma Strubell Niranjan Balasubramanian Leon Derczynski Iryna Gurevych Roy Schwartz 28 109 0 31 Aug 2022
Context-Aware Streaming Perception in Dynamic Environments Gur-Eyal Sela Ionel Gog J. Wong Kumar Krishna Agrawal Xiangxi Mo ... Eric Leong Xin Wang Bharathan Balaji Joseph E. Gonzalez Ion Stoica 12 9 0 16 Aug 2022
Exploring the Design of Adaptation Protocols for Improved Generalization and Machine Learning Safety Puja Trivedi Danai Koutra Jayaraman J. Thiagarajan AAML 22 0 0 26 Jul 2022
Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration Bohua Peng Mobarakol Islam Mei Tu UQCV 11 9 0 18 Jul 2022
A Study on the Predictability of Sample Learning Consistency Alain Raymond-Sáez J. Hurtado Alvaro Soto 13 0 0 07 Jul 2022
Studying the impact of magnitude pruning on contrastive learning methods Francesco Corti R. Entezari Sara Hooker D. Bacciu O. Saukh 11 5 0 01 Jul 2022
Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning Florian Bordes Randall Balestriero Q. Garrido Adrien Bardes Pascal Vincent 22 22 0 27 Jun 2022
When Does Re-initialization Work? Sheheryar Zaidi Tudor Berariu Hyunjik Kim J. Bornschein Claudia Clopath Yee Whye Teh Razvan Pascanu 35 10 0 20 Jun 2022
Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks Mansheej Paul Brett W. Larsen Surya Ganguli Jonathan Frankle Gintare Karolina Dziugaite 20 24 0 02 Jun 2022
Selective Classification Via Neural Network Training Dynamics Stephan Rabanser Anvith Thudi Kimia Hamidieh Adam Dziedzic Nicolas Papernot 21 21 0 26 May 2022
The Effect of Task Ordering in Continual Learning Samuel J. Bell Neil D. Lawrence CLL 46 17 0 26 May 2022
Unintended memorisation of unique features in neural networks J. Hartley Sotirios A. Tsaftaris 30 1 0 20 May 2022
Understanding out-of-distribution accuracies through quantifying difficulty of test samples Berfin Simsek Melissa Hall Levent Sagun 23 5 0 28 Mar 2022
Representative Subset Selection for Efficient Fine-Tuning in Self-Supervised Speech Recognition Abdul Hameed Azeemi I. Qazi Agha Ali Raza 21 0 0 18 Mar 2022
Layer Ensembles: A Single-Pass Uncertainty Estimation in Deep Learning for Segmentation Kaisar Kushibar Víctor M. Campello Lidia Garrucho Moras Akis Linardos P. Radeva Karim Lekadir UQCV 8 18 0 16 Mar 2022
py-irt: A Scalable Item Response Theory Library for Python John P. Lalor Pedro Rodriguez 20 10 0 02 Mar 2022
Deconstructing Distributions: A Pointwise Framework of Learning Gal Kaplun Nikhil Ghosh Saurabh Garg Boaz Barak Preetum Nakkiran OOD 25 21 0 20 Feb 2022
Measuring Unintended Memorisation of Unique Private Features in Neural Networks J. Hartley Sotirios A. Tsaftaris 19 7 0 16 Feb 2022
Predicting on the Edge: Identifying Where a Larger Model Does Better Taman Narayan Heinrich Jiang Sen Zhao Surinder Kumar 23 7 0 15 Feb 2022
Fortuitous Forgetting in Connectionist Networks Hattie Zhou Ankit Vani Hugo Larochelle Aaron Courville CLL 6 42 0 01 Feb 2022
Nearest Class-Center Simplification through Intermediate Layers Ido Ben-Shaul S. Dekel 38 26 0 21 Jan 2022
Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning Utku Evci Vincent Dumoulin Hugo Larochelle Michael C. Mozer 23 83 0 10 Jan 2022