![[Conference on Parsimony and Learning Logo]](/v280/assets/images/logo-pmlr.svg){kind=logo}
[edit]
Volume 280: Conference on Parsimony and Learning, 24-27 March 2025, Stanford University, USA
[edit]
Editors: Beidi Chen, Shijia Liu, Mert Pilanci, Weijie Su, Jeremias Sulam, Yuxiang Wang, Zhihui Zhu
Approximate Nullspace Augmented Finetuning for Robust Vision Transformers
; Conference on Parsimony and Learning, PMLR 280:1-23
Fast John Ellipsoid Computation with Differential Privacy Optimization
; Conference on Parsimony and Learning, PMLR 280:24-64
Large-Scale Multiway Clustering with Seeded Clustering
; Conference on Parsimony and Learning, PMLR 280:65-88
Learning of Patch-Based Smooth-Plus-Sparse Models for Image Reconstruction
; Conference on Parsimony and Learning, PMLR 280:89-104
HSR-Enhanced Sparse Attention Acceleration
; Conference on Parsimony and Learning, PMLR 280:105-133
AdaProx: A Novel Method for Bilevel Optimization under Pessimistic Framework
; Conference on Parsimony and Learning, PMLR 280:134-164
A Case Study of Low Ranked Self-Expressive Structures in Neural Network Representations
; Conference on Parsimony and Learning, PMLR 280:165-236
Do Global and Local Perform Cooperatively or Adversarially in Heterogeneous Federated Learning?
; Conference on Parsimony and Learning, PMLR 280:237-254
Heterogeneous Decision Making in Mixed Traffic: Uncertainty-aware Planning and Bounded Rationality
; Conference on Parsimony and Learning, PMLR 280:255-277
Adaptive Batch Size Schedules for Distributed Training of Language Models with Data and Model Parallelism
; Conference on Parsimony and Learning, PMLR 280:278-304
Revisiting the Initial Steps in Adaptive Gradient Descent Optimization
; Conference on Parsimony and Learning, PMLR 280:305-322
A Validation Approach to Over-parameterized Matrix and Image Recovery
; Conference on Parsimony and Learning, PMLR 280:323-350
Dual Reasoning: A GNN-LLM Collaborative Framework for Knowledge Graph Question Answering
; Conference on Parsimony and Learning, PMLR 280:351-372
Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function Approximation
; Conference on Parsimony and Learning, PMLR 280:373-391
Provable Model-Parallel Distributed Principal Component Analysis with Parallel Deflation
; Conference on Parsimony and Learning, PMLR 280:392-416
Meta ControlNet: Enhancing Task Adaptation via Meta Learning
; Conference on Parsimony and Learning, PMLR 280:417-432
Concept Bottleneck Model with Zero Performance Loss
; Conference on Parsimony and Learning, PMLR 280:433-461
FedPeWS: Personalized Warmup via Subnetworks for Enhanced Heterogeneous Federated Learning
; Conference on Parsimony and Learning, PMLR 280:462-483
A unified framework for Sparse plus Low-Rank Matrix Decomposition for LLMs
; Conference on Parsimony and Learning, PMLR 280:484-499
Greedy Output Approximation: Towards Efficient Structured Pruning for LLMs Without Retraining
; Conference on Parsimony and Learning, PMLR 280:500-520
MoXCo: How I learned to stop exploring and love my local minima?
; Conference on Parsimony and Learning, PMLR 280:521-544
Unlock the Theory behind Scaling 1-bit Neural Networks
; Conference on Parsimony and Learning, PMLR 280:545-598
Bridging Domain Adaptation and Graph Neural Networks: A Tensor-Based Framework for Effective Label Propagation
; Conference on Parsimony and Learning, PMLR 280:599-614
Theoretical and Empirical Advances in Forest Pruning
; Conference on Parsimony and Learning, PMLR 280:615-651
Asymptotic Behavior of the Coordinate Ascent Variational Inference in Singular Models
; Conference on Parsimony and Learning, PMLR 280:652-674
Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond
; Conference on Parsimony and Learning, PMLR 280:675-738
The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity
; Conference on Parsimony and Learning, PMLR 280:739-767
Grouped Sequential Optimization Strategy - the Application of Hyperparameter Importance Assessment in Deep Learning
; Conference on Parsimony and Learning, PMLR 280:768-779
You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time
; Conference on Parsimony and Learning, PMLR 280:780-809
Improving Neuron-level Interpretability with White-box Language Models
; Conference on Parsimony and Learning, PMLR 280:810-836
Quantum EigenGame for excited state calculation
; Conference on Parsimony and Learning, PMLR 280:837-864
Adversarially Robust Spiking Neural Networks with Sparse Connectivity
; Conference on Parsimony and Learning, PMLR 280:865-883
Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization
; Conference on Parsimony and Learning, PMLR 280:884-896
RecCrysFormer: Refined Protein Structural Prediction from 3D Patterson Maps via Recycling Training Runs
; Conference on Parsimony and Learning, PMLR 280:897-912
Learning Effective Dynamics across Spatio-Temporal Scales of Complex Flows
; Conference on Parsimony and Learning, PMLR 280:913-931
Fast and Efficient Matching Algorithm with Deadline Instances
; Conference on Parsimony and Learning, PMLR 280:932-959
Closure Discovery for Coarse-Grained Partial Differential Equations Using Grid-based Reinforcement Learning
; Conference on Parsimony and Learning, PMLR 280:960-984
FedOSAA: Improving Federated Learning with One-Step Anderson Acceleration
; Conference on Parsimony and Learning, PMLR 280:985-1006
Enhancing Video Representation Learning with Temporal Differentiation
; Conference on Parsimony and Learning, PMLR 280:1007-1034
Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients
; Conference on Parsimony and Learning, PMLR 280:1035-1050
Vanishing Feature: Diagnosing Model Merging and Beyond
; Conference on Parsimony and Learning, PMLR 280:1051-1086
Exact and Rich Feature Learning Dynamics of Two-Layer Linear Networks
; Conference on Parsimony and Learning, PMLR 280:1087-1111
Sparse MoE as a New Treatment: Addressing Forgetting, Fitting, Learning Issues in Multi-Modal Multi-Task Learning
; Conference on Parsimony and Learning, PMLR 280:1112-1145
AgentHPO: Large Language Model Agent for Hyper-Parameter Optimization
; Conference on Parsimony and Learning, PMLR 280:1146-1169
Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
; Conference on Parsimony and Learning, PMLR 280:1170-1190
Sufficient and Necessary Explanations (and What Lies in Between)
; Conference on Parsimony and Learning, PMLR 280:1191-1215
Streaming Kernel PCA Algorithm With Small Space
; Conference on Parsimony and Learning, PMLR 280:1216-1254
Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets
; Conference on Parsimony and Learning, PMLR 280:1255-1273
How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks
; Conference on Parsimony and Learning, PMLR 280:1274-1291
White-box Error Correction Code Transformer
; Conference on Parsimony and Learning, PMLR 280:1292-1306
Are all layers created equal: A neural collapse perspective
; Conference on Parsimony and Learning, PMLR 280:1307-1327
Collaborative and Efficient Personalization with Mixtures of Adaptors
; Conference on Parsimony and Learning, PMLR 280:1328-1364
Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning
; Conference on Parsimony and Learning, PMLR 280:1365-1387
SGD with Weight Decay Secretly Minimizes the Ranks of Your Neural Networks
; Conference on Parsimony and Learning, PMLR 280:1388-1412
Towards Vector Optimization on Low-Dimensional Vector Symbolic Architecture
; Conference on Parsimony and Learning, PMLR 280:1413-1432
subscribe via RSS