Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous\n Distributed Learning
Bibliographic record
Abstract
A commonly cited inefficiency of neural network training using\nback-propagation is the update locking problem: each layer must wait for the\nsignal to propagate through the full network before updating. Several\nalternatives that can alleviate this issue have been proposed. In this context,\nwe consider a simple alternative based on minimal feedback, which we call\nDecoupled Greedy Learning (DGL). It is based on a classic greedy relaxation of\nthe joint training objective, recently shown to be effective in the context of\nConvolutional Neural Networks (CNNs) on large-scale image classification. We\nconsider an optimization of this objective that permits us to decouple the\nlayer training, allowing for layers or modules in networks to be trained with a\npotentially linear parallelization. With the use of a replay buffer we show\nthat this approach can be extended to asynchronous settings, where modules can\noperate and continue to update with possibly large communication delays. To\naddress bandwidth and memory issues we propose an approach based on online\nvector quantization. This allows to drastically reduce the communication\nbandwidth between modules and required memory for replay buffers. We show\ntheoretically and empirically that this approach converges and compare it to\nthe sequential solvers. We demonstrate the effectiveness of DGL against\nalternative approaches on the CIFAR-10 dataset and on the large-scale ImageNet\ndataset.\n
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".