{"total":41,"rows":[{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164,"area":null},{"id":"2302.14838","title":"EvoPrompting: Language Models for Code-Level Neural Architecture Search","created":"2023-02-28","cited_by_count":131,"area":null},{"id":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69,"area":null},{"id":"2105.07576","title":"Rethinking \"Batch\" in BatchNorm","created":"2021-05-17","cited_by_count":45,"area":null},{"id":"2110.04175","title":"RelaySum for Decentralized Deep Learning on Heterogeneous Data","created":"2021-10-08","cited_by_count":39,"area":null},{"id":"2106.05956","title":"Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning","created":"2021-06-10","cited_by_count":25,"area":null},{"id":"2102.04700","title":"Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search","created":"2021-02-09","cited_by_count":20,"area":null},{"id":"2103.14026","title":"AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks","created":"2021-03-25","cited_by_count":19,"area":null},{"id":"2203.07976","title":"On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2106.03743","title":"Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2204.06477","title":"Data-heterogeneity-aware Mixing for Decentralized Learning","created":"2022-04-13","cited_by_count":12,"area":null},{"id":"2305.04792","title":"Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data","created":"2023-05-08","cited_by_count":12,"area":null},{"id":"2106.03640","title":"Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training","created":"2021-06-07","cited_by_count":6,"area":null},{"id":"2109.08958","title":"AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks","created":"2021-09-18","cited_by_count":5,"area":null},{"id":"2209.14390","title":"Neighborhood Gradient Clustering: An Efficient Decentralized Learning Method for Non-IID Data Distributions","created":"2022-09-28","cited_by_count":5,"area":null},{"id":"2301.05785","title":"Efficient Activation Function Optimization through Surrogate Modeling","created":"2023-01-13","cited_by_count":5,"area":null},{"id":"2110.08429","title":"TorchEsegeta: Framework for Interpretability and Explainability of Image-based Deep Learning Models","created":"2021-10-16","cited_by_count":4,"area":null},{"id":"2210.11407","title":"Similarity of Neural Architectures using Adversarial Attack Transferability","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2103.03905","title":"Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory","created":"2021-02-20","cited_by_count":3,"area":null},{"id":"2112.10474","title":"Reciprocal Normalization for Domain Adaptation","created":"2021-12-20","cited_by_count":3,"area":null},{"id":"2102.06120","title":"Deep Photo Scan: Semi-Supervised Learning for dealing with the real-world degradation in Smartphone Photo Scanning","created":"2021-02-11","cited_by_count":2,"area":null},{"id":"2111.09389","title":"Low Precision Decentralized Distributed Training over IID and non-IID Data","created":"2021-11-17","cited_by_count":2,"area":null},{"id":"2302.05433","title":"Unified Functional Hashing in Automatic Machine Learning","created":"2023-02-10","cited_by_count":2,"area":null},{"id":"2305.15945","title":"Learning to Act through Evolution of Neural Diversity in Random Neural Networks","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2403.08793","title":"Neural Loss Function Evolution for Large-Scale Image Classifier Convolutional Neural Networks","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2404.00521","title":"CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2206.03291","title":"GAAF: Searching Activation Functions for Binary Neural Networks through Genetic Algorithm","created":"2022-06-05","cited_by_count":1,"area":null},{"id":"2404.05919","title":"AdaGossip: Adaptive Consensus Step-size for Decentralized Deep Learning with Communication Compression","created":"2024-04-09","cited_by_count":1,"area":null},{"id":"2408.06820","title":"Efficient Search for Customized Activation Functions with Gradient Descent","created":"2024-08-13","cited_by_count":1,"area":null},{"id":"2105.02752","title":"Modeling the geospatial evolution of COVID-19 using spatio-temporal convolutional sequence-to-sequence neural networks","created":"2021-05-06","cited_by_count":0,"area":null},{"id":"2206.03325","title":"Searching Similarity Measure for Binarized Neural Networks","created":"2022-06-05","cited_by_count":0,"area":null},{"id":"2210.09083","title":"Nish: A Novel Negative Stimulated Hybrid Activation Function","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2309.11246","title":"Grassroots Operator Search for Model Edge Adaptation","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2310.15890","title":"Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2403.16798","title":"Enhancing Neural Network Representations with Prior Knowledge-Based Normalization","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2404.06679","title":"Neural Optimizer Equation, Decay Function, and Learning Rate Schedule Joint Evolution","created":"2024-04-10","cited_by_count":0,"area":null},{"id":"2405.13961","title":"SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2408.03599","title":"Activations Through Extensions: A Framework To Boost Performance Of Neural Networks","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2606.02927","title":"SaluNet: Enabling Total Plasticity in Normalization-Free Deep Networks","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.30398","title":"ENC-ODE: Event-level Neurodegenerative Modeling in Continuous Time with Neural ODEs","created":"2026-06-29","cited_by_count":0,"area":null}],"next_cursor":null}