No article text was recorded for this version.
linear memory scaling (per-sample state overhead)
Version 2 of 280 papers81 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Online Knowledge Distillation by Temporal-Spatial Boosting
- Blog: Fast Cross-Validation for Incremental Learning
- Blog: Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface
- Blog: EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence
- Blog: EMC2: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence
- Blog: Optimal Algorithms for Lipschitz Bandits with Heavy-tailed Rewards
- Blog: Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence
- Blog: Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples
- Blog: Fast Gumbel-Max Sketch and its Applications
- Blog: MCA: 2D-3D Retrieval with Noisy Labels via Multi-level Adaptive Correction and Alignment
- Blog: In-context Reinforcement Learning with Algorithm Distillation
- Blog: A Stochastic Path Integral Differential EstimatoR Expectation Maximization Algorithm
- Blog: Carpe Diem, Seize the Samples Uncertain "At the Moment" for Adaptive Batch Selection
- Blog: RepFace: Refining Closed-Set Noise with Progressive Label Correction for Face Recognition
- Blog: SampleSearch: A Scheme that Searches for Consistent Samples
- Blog: Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence
- Blog: Maximum-Margin Hamming Hashing
- Blog: D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition
- Blog: Group Meritocratic Fairness in Linear Contextual Bandits
- Blog: Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure
- Blog: Better Supervisory Signals by Observing Learning Paths
- Blog: Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence
- Blog: Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning
- Blog: Transductive CLIP with Class-Conditional Contrastive Learning
- Blog: Exploring Memorization in Adversarial Training
- Blog: Efficient Bias Mitigation Without Privileged Information
- Blog: MILD: Modeling the Instance Learning Dynamics for Learning with Noisy Labels
- Blog: Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?
- Blog: Prior-Guided Adversarial Initialization for Fast Adversarial Training
- Blog: ADAM Optimization with Adaptive Batch Selection
- Blog: Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification
- Blog: Firefly Monte Carlo: Exact MCMC with Subsets of Data
- Blog: EMC2: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence
- Blog: Directly Denoising Diffusion Models
- Blog: Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling
- Blog: On the Global Convergence of (Fast) Incremental Expectation Maximization Methods
- Blog: Bayesian Self-Distillation for Image Classification
- Blog: Towards Semi-supervised Learning with Non-random Missing Labels
- Blog: Prior-Fitted Networks Scale to Larger Datasets When Treated as Weak Learners
- Blog: DynHAC: Fully Dynamic Approximate Hierarchical Agglomerative Clustering
- Blog: Joint control variate for faster black-box variational inference
- Blog: Particle Gibbs for Bayesian Additive Regression Trees
- Blog: SELFIE: Refurbishing Unclean Samples for Robust Deep Learning
- Blog: Towards Interactive Debugging of Rule-based Entity Matching
- Blog: ChronoSelect: Robust Learning with Noisy Labels via Dynamics Temporal Memory
- Blog: Faking Interpolation Until You Make It
- Blog: MILD: Modeling the Instance Learning Dynamics for Learning with Noisy Labels
- Blog: Explain by Evidence: An Explainable Memory-based Neural Network for Question Answering
- Blog: A System for Studying Deep Network Training
- Blog: Barely-Supervised Learning: Semi-supervised Learning with Very Few Labeled Images
- Blog: Provable Multi-instance Deep AUC Maximization with Stochastic Pooling
- Blog: When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee
- Blog: Hard Sample Aware Noise Robust Learning for Histopathology Image Classification
- Blog: Sharpness-Aware Training for Free
- Blog: Adaptive Monte Carlo Multiple Testing via Multi-Armed Bandits
- Blog: Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling
- Blog: A Probabilistic Framework for Adapting to Changing and Recurring Concepts in Data Streams
- Blog: Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks
- Blog: SVARM-IQ: Efficient Approximation of Any-order Shapley Interactions through Stratification
- Blog: MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins
Showing 60 of 80 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_linear_memory_scaling_per_sample_state_o_e3360663,
title = {linear memory scaling (per-sample state overhead)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/linear-memory-scaling-per-sample-state-overhead/rdr_e3360663a3264ca2aaac04f19beb157d},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 2, frozen text):
@misc{lacuna_linear_memory_scaling_per_sample_state_o_e3360663_v2,
title = {linear memory scaling (per-sample state overhead)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/linear-memory-scaling-per-sample-state-overhead/rdr_e3360663a3264ca2aaac04f19beb157d/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-22},
}