In high-dimensional continual linear regression, optimal fixed L2 regularization strength scales as T/ln T with the number of tasks and mitigates label noise for arbitrary linear teachers.
Canonical reference
URL https: //www.pnas.org/doi/abs/10.1073/pnas.1611835114
Canonical reference. 90% of citing Pith papers cite this work as background.
73
Pith papers citing it
5,466
external citations · Crossref
Background
90% of classified citations
citation-role summary
background 9
method 1
citation-polarity summary
representative citing papers
CARLOS employs an aggregate deep neural network trained on progressively finer time grids with adaptive sampling to learn continuous-time exercise boundaries for optimal stopping, delivering higher values than discrete Bermudan methods.
EST-PRM stress-tests five PRM models on 4,687 reasoning chains from MATH-500, GSM8K, and PRMBench using three label-preserving transformations and reports model-specific vulnerability patterns.
Formalizes continual model routing (CMR), releases CMRBench with over 2000 models, and presents CARvE which outperforms retrieval, fine-tuning and adapter-merging baselines on model/family/domain accuracy.
Introduces Unlearning Depth Score (UDS) via activation patching to quantify LLM unlearning depth and claims it outperforms 20 other metrics in faithfulness and robustness on 150 models.
Creates realistic benchmarks for continual anomaly detection and proposes DINOSaur, a training-free method with frozen DINOv3, coreset memory, and neighborhood scoring that outperforms others with zero forgetting and sub-100ms edge inference.
PMF-CL derives Pareto-minimal-forgetting algorithms for linear/basis-function regression and quadratic-bounded losses like logistic regression, achieving static O(d²) memory for d-parameter models.
Formalizes Reasoning Portability (RP) and proposes RDB-CL to modulate per-sample KL regularization in RLVR for MLLM continual learning, achieving +12.0% Last accuracy over vanilla RLVR baseline by preserving reusable reasoning on high-RP samples.
Pre-pretraining on MP-STRUCT matches k-Shuffle Dyck baselines in efficiency while adding human-like resistance to implausible languages and challenges the need for C-RASP definability in effective PPT languages.
Fuzzy ARTMAP models are highly vulnerable to a new white-box attack aligned with their category competition, but progressive selective training yields stronger replay-free robustness than offline adversarial training under adaptive evaluation.
A cross-version swap protocol reveals dominant skills that swing composition success by up to 50 percentage points, and an atomic probe with selective revalidation governs updates at lower cost than always re-testing full compositions.
Preconditioned delta-rule models with a diagonal curvature approximation improve upon standard DeltaNet, GDN, and KDA by better approximating the test-time regression objective.
CapTrack shows post-training causes drift beyond facts, with instruction fine-tuning producing stronger behavioral changes than preference optimization across model families.
LoRA adapters should be scaled by 1/sqrt(rank) rather than 1/rank to stabilize learning and enable effective use of higher ranks during fine-tuning of large language models.
Quality-aware self-distillation using soft correctness-aware gating and teacher-probability scaling improves VLM performance on GUI grounding benchmarks when both components are combined.
RLVR exhibits correct-set turnover where solved problems regress during training, and a periodic review mechanism exploiting a repair-window principle improves retention and performance over baselines.
Structured text representations like CML and MolJSON outperform SMILES variants on structural tasks while IUPAC dominates semantic tasks such as molecule retrieval across all tested LLMs.
AdvCL repurposes adversarial perturbations into geometric control signals for continual learning using Intra-Smooth, Proto-Clip, and Inter-Align modules, reporting gains in performance, robustness, lower forgetting, and stronger transfer.
PROXYMIX learns a dynamic replay controller on a small proxy model and transfers it to a large target model, improving accuracy by 3.4 points and reducing forgetting by 3.5 points on LLaMA-3-8B continual tuning sequences.
Divergence Decoding steers LLM logits using small auxiliary models to unlearn specific data at inference time, outperforming baselines and generalizing to images.
Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phases and mistakes.
TypedCSIP applies typed counterfactual selective intervention pretraining on expert revisions to lift macro-F1 by 0.9-1.3 pp on the LCR-CN Chinese legislative conflict classification benchmark under a pre-registered multi-seed test.
Introduces a representation-geometry-based taxonomy for continual learning in speech and audio, identifies mismatches with current CL assumptions in foundation models, and lists open challenges.
2D-ProteinRAG is a dual-dimensional RAG framework that incorporates BLAST workflows plus horizontal attribute alignment and vertical homology denoising to improve protein-text QA on both in-distribution and out-of-distribution cases.
citing papers explorer
No citing papers match the current filters.