Papers with Code 아카이브

Learning Theory

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/cleverhans-lab/practical-attacks-against-pol

공식 코드

Proof-of-Learning is Currently More Broken Than You Think

https://github.com/cltan023/stablesam2024

공식 코드

Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy

https://github.com/col-tasas/2024-bilinear-end-to-end

공식 코드

End-to-end guarantees for indirect data-driven control of bilinear systems with finite stochastic data

https://github.com/csinva/mdl-complexity

공식 코드

Revisiting minimum description length complexity in overparameterized models

https://github.com/cxtraa/ngd_with_slt

공식 코드

NGD converges to less degenerate solutions than SGD

https://github.com/dadacheng/smgcn

공식 코드

Homophily modulates double descent generalization in graph convolution networks

https://github.com/dassein/cycloid_em_mlr

공식 코드

Unveiling the Cycloid Trajectory of EM Iterations in Mixed Linear Regression

https://github.com/data-designer/da

공식 코드

Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment

https://github.com/ddm-lab/greedy-hysteretic-lenient-maibl

공식 코드

Learning in Cooperative Multiagent Systems Using Cognitive and Machine Models

https://github.com/ddm-lab/speedyibl

공식 코드

SpeedyIBL: A Comprehensive, Precise, and Fast Implementation of Instance-Based Learning Theory

https://github.com/delta2323/GB-GNN

공식 코드

Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks

https://github.com/diegodoimo/redundant_representation

공식 코드

Redundant representations help generalization in wide neural networks

https://github.com/divelab/atta

공식 코드

Active Test-Time Adaptation: Theoretical Analyses and An Algorithm

https://github.com/edmundlth/scalable_learning_coefficient_with_sgld

공식 코드

The Local Learning Coefficient: A Singularity-Aware Complexity Measure

https://github.com/elkabzo/cont_disc_opt_dnn

공식 코드

Continuous vs. Discrete Optimization of Deep Neural Networks

https://github.com/emalach/IsDeeperBetter

공식 코드

Is Deeper Better only when Shallow is Good?

https://github.com/emsansone/USMO

공식 코드

Efficient Training for Positive Unlabeled Learning

https://github.com/facebookresearch/alma

공식 코드

On Anytime Learning at Macroscale

https://github.com/facebookresearch/directclr

공식 코드

Understanding Dimensional Collapse in Contrastive Self-supervised Learning

https://github.com/ftramer/Steal-ML

공식 코드

Stealing Machine Learning Models via Prediction APIs

https://github.com/gbdl/ecdsep

공식 코드

Improving Energy Conserving Descent for Machine Learning: Theory and Practice

https://github.com/gdebarghya/Network-TwoSampleTesting

공식 코드

Practical methods for graph two-sample testing

https://github.com/ghliu/mean-field-fcdnn

공식 코드

Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective

https://github.com/goldblum/TruthOrBackpropaganda

공식 코드

Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory

https://github.com/google-research/pactran_metrics

공식 코드

PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks

https://github.com/gortizji/inr_dictionaries

공식 코드

A Structured Dictionary Perspective on Implicit Neural Representations

https://github.com/grasp-lyrl/modelzoo_continual

공식 코드

Model Zoo: A Growing "Brain" That Learns Continually

https://github.com/gregorbachmann/scaling_mlps

공식 코드

Scaling MLPs: A Tale of Inductive Bias

https://github.com/gyauney/data-label-alignment

공식 코드

Comparing Text Representations: A Theory-Driven Approach

https://github.com/helena-yuhan-liu/biolhessrnn

공식 코드

Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules

https://github.com/hugoschmutz/defixmatch

공식 코드

Don't fear the unlabelled: safe semi-supervised learning via simple debiasing

https://github.com/iancovert/data-scaling

공식 코드

Scaling Laws for the Value of Individual Data Points in Machine Learning

https://github.com/ikelq/Enhanced-PID-Adaptive-Feedforward-Neural-Network-Control

공식 코드

Adaptive Feedforward Neural Network Control with an Optimized Hidden Node Distribution

https://github.com/insou/pop_minima

공식 코드

On generalization bounds for deep networks based on loss surface implicit regularization

https://github.com/ist-daslab/spade

공식 코드

SPADE: Sparsity-Guided Debugging for Deep Neural Networks

https://github.com/james-simon/eigenlearning

공식 코드

The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural Networks

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.