Pith. sign in

REVIEW 1 cited by

Primal Dual Continual Learning: Balancing Stability and Plasticity through Adaptive Memory Allocation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.00154 v2 pith:V7DS22FR submitted 2023-09-29 cs.LG cs.AIeess.SP

classification cs.LGcs.AIeess.SP
keywords learningcontinualproblemapproachconstrainedbufferdualcoarse
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Continual learning is inherently a constrained learning problem. The goal is to learn a predictor under a no-forgetting requirement. Although several prior studies formulate it as such, they do not solve the constrained problem explicitly. In this work, we show that it is both possible and beneficial to undertake the constrained optimization problem directly. To do this, we leverage recent results in constrained learning through Lagrangian duality. We focus on memory-based methods, where a small subset of samples from previous tasks can be stored in a replay buffer. In this setting, we analyze two versions of the continual learning problem: a coarse approach with constraints at the task level and a fine approach with constraints at the sample level. We show that dual variables indicate the sensitivity of the optimal value of the continual learning problem with respect to constraint perturbations. We then leverage this result to partition the buffer in the coarse approach, allocating more resources to harder tasks, and to populate the buffer in the fine approach, including only impactful samples. We derive a deviation bound on dual variables as sensitivity indicators, and empirically corroborate this result in diverse continual learning benchmarks. We also discuss the limitations of these methods with respect to the amount of memory available and the expressiveness of the parametrization.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Constrained Sliced Wasserstein Embedding

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Adding SWGG dissimilarity constraints to sliced Wasserstein embedding, trained via primal-dual optimization with a softsort relaxation, improves pooling accuracy on image, point cloud, and protein-sequence benchmarks.

Pith tools