Papers › Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize,...

Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How

8 Nov 2023arXiv:2311.04898archive 2025-07-28

Timm Hess, Tinne Tuytelaars, Gido M. van de Ven

Recent years have seen considerable progress in the continual training of deep neural networks, predominantly thanks to approaches that add replay or regularization terms to the loss function to approximate the joint loss over all tasks so far. However, we show that even with a perfect approximation to the joint loss, these approaches still suffer from temporary but substantial forgetting when starting to train on a new task. Motivated by this 'stability gap', we propose that continual learning strategies should focus not only on the optimization objective, but also on the way this objective is optimized. While there is some continual learning work that alters the optimization trajectory (e.g., using gradient projection techniques), this line of research is positioned as alternative to improving the optimization objective, while we argue it should be complementary. In search of empirical support for our proposition, we perform a series of pre-registered experiments combining replay-approximated joint objectives with gradient projection-based optimization routines. However, this first experimental attempt fails to show clear and consistent benefits. Nevertheless, our conceptual arguments, as well as some of our empirical results, demonstrate the distinctive importance of the optimization trajectory in continual learning, thereby opening up a new direction for continual learning research.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 9 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

timmhess/twocomplementaryperspectivescl officialmentioned in paperpytorchMITSyntology: 9 samples, 9 ran (0 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran

Licence: 0 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from timmhess/twocomplementaryperspectivescl. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

timmhess/twocomplementaryperspectivescl official repository 9 samples, 9 ran (0 instrument-failed) · 0 unverified
AE_loss avalanche/models/expert_gate.py ran fingerprinted MIT (permissive) · 16b9e00f007a0abf · report fixture: signature target:Tensor/2/float, reconstruction:Tensor/2/float · returned Tensor · level recorded 2026-09-24
check_overwrite_directory helper.py ran fingerprinted MIT (permissive) · baa60c6b90daab7c · report fixture: signature s:str/0/str · returned tuple · level recorded 2026-09-24
compare_keys avalanche/models/dynamic_optimizers.py ran MIT (permissive) · 4468c94aca4d060f · report fixture: signature old_dict:dict/0/?, new_dict:dict/0/? · returned tuple · level recorded 2026-09-24
cut_string helper.py ran fingerprinted MIT (permissive) · 1c48b422727921a2 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
deprecated in 25 papers avalanche/_annotations.py ran MIT (permissive) · 667a50347702db96 · report fixture: signature version:float/0/float, reason:str/0/str · returned function · level recorded 2026-09-24
experimental avalanche/_annotations.py ran MIT (permissive) · 9bd77285b9ea9767 · report fixture: signature reason:str/0/str · returned function · level recorded 2026-09-24
get_transforms in 40 papers helper.py ran MIT (permissive) · c3dd6c1f097353b6 · report fixture: signature data_aug:str/0/str, input_size:tuple/1/int, norm_mean:tuple/1/float, norm_std:tuple/1/float, use_to_pil:bool/0/bool, use_corruption:bool/0/bool · returned tuple · level recorded 2026-09-24
reset_optimizer avalanche/models/dynamic_optimizers.py ran MIT (permissive) · 551c67f1ad0c8a2c · report fixture: signature optimizer:SGD/0/?, model:callable/0/? · returned dict · level recorded 2026-09-24
update_optimizer avalanche/models/dynamic_optimizers.py ran MIT (permissive) · d0dc299a23419623 · report fixture: signature optimizer:SGD/0/?, new_params:dict/0/?, optimized_params:dict/0/?, reset_state:bool/0/bool · returned dict · level recorded 2026-09-24

Tasks

Continual Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections