Ctrl+K

1 contributor

History: 19 commits

ProCreations

Repair convergence and falsify LrGW memory claim

85afda5 about 9 hours ago

code
Repair convergence and falsify LrGW memory claim about 9 hours ago
outputs
Claim 1: rebuild the solver without a dense cost matrix; peak heap scales as N^1.13 against N^2.00 for the dense reference. 4 days ago
packaged_replay
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
pages
Repair convergence and falsify LrGW memory claim about 9 hours ago
repro_code
Add entropic Gromov-Wasserstein experiments 6 days ago
source
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
.gitattributes

1.88 kB
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
BUNDLE_SHA256SUMS.txt

6.33 kB
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
README.md

665 Bytes
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
SOURCE_PIN.txt

639 Bytes
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
bucket-icon.svg

413 Bytes
Publish independent ICML 2026 reproduction: Optimal Unconstrained Self-Distillation 12 days ago
build_manifest.py

952 Bytes
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
claims.json

1.19 kB
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
index.html

1.85 kB
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
linear_memory_gw.py

5.54 kB
Claim 1: rebuild the solver without a dense cost matrix; peak heap scales as N^1.13 against N^2.00 for the dense reference. 4 days ago
logbook.css

29.6 kB
Publish independent ICML 2026 reproduction: Optimal Unconstrained Self-Distillation 12 days ago
logbook.js

77.3 kB
Publish independent ICML 2026 reproduction: Optimal Unconstrained Self-Distillation 12 days ago
logbook.json

5.13 kB
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
official_claims.json

1.19 kB
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
outputs_gw2_results.json

2.73 kB
Claim 1: measure real wall-time/peak-heap scaling (slopes 1.85/1.95) instead of counting operations. Claim 5: test SGW non-negativity on CNT costs (tree metrics, circle geodesics) with a corrected isometric control 6 days ago
outputs_gw5_results.json

7.55 kB
Claim 3: verify Theorem 3.4's reduction via the Krein GW-embedding identity (quartic contraction vs Hilbert-Schmidt form) to 1.7e-14 at n=180 on three CNT families, for arbitrary couplings 6 days ago
outputs_gw6_results.json

3.34 kB
Claim 4: test descent from a random initialisation at n=400/200 iters (28-93% decrease); monotone in 8/9 cells, symmetric-instance exception attributed to entropic instability 6 days ago
outputs_gw7_results.json

2.78 kB
Claim 6: verify the GW gradient to measured order 2.00 across three CNT families at n=150, and run gradient descent that monotonically reduces the loss at n up to 300 6 days ago
poster_embed.html

1.62 kB
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
reproduce.py

19.6 kB
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
requirements.txt

32 Bytes
Repurpose zero-loss duplicate for Gromov-Wasserstein scale reproduction 9 days ago
trackio-logo-light.png

30 kB
Publish independent ICML 2026 reproduction: Optimal Unconstrained Self-Distillation 12 days ago
trackio-logo.png

55.6 kB
Publish independent ICML 2026 reproduction: Optimal Unconstrained Self-Distillation 12 days ago
trackio-wordmark-dark.png

89.8 kB
Publish independent ICML 2026 reproduction: Optimal Unconstrained Self-Distillation 12 days ago