Exact algorithms and lower bounds for stable instances of euclidean k-means
Bibliographic record
Abstract
We investigate the complexity of solving stable or perturbation-resilient instances of k-means and k-median clustering in fixed dimension Euclidean metrics (or more generally doubling metrics). The notion of stable or perturbation resilient instances was introduced by Bilu and Linial [2010] and Awasthi, Blum, and Sheffet [2012]. In our context, we say a k-means instance is α-stable if there is a unique optimum solution which remains unchanged if distances are (non-uniformly) stretched by a factor of at most α. Stable clustering instances have been studied to explain why heuristics such as Lloyd's algorithm perform well in practice. In this work we show that for any fixed ϵ > 0, (1 + ϵ)-stable instances of k-means in doubling metrics, which include fixed-dimensional Euclidean metrics, can be solved in polynomial time. More precisely, we show a natural multi-swap local-search algorithm in fact finds the optimum solution for (1 + ϵ)-stable instances of k-means and k-median in a polynomial number of iterations.We complement this result by showing that under a plausible PCP hypothesis this is essentially tight: that when the dimension d is part of the input, there is a fixed ϵ0 > 0 such there is not even a PTAS for (1 + ϵ0)-stable k-means in Rd unless NP=RP. To do this, we consider a robust property of CSPs; call an instance stable if there is a unique optimum solution x* and for any other solution x', the number of unsatisfied clauses is proportional to the Hamming distance between x* and x'. Dinur, Goldreich, and Gur have already shown stable QSAT is hard to approximation for some constant Q [16], our hypothesis is simply that stable QSAT with bounded variable occurrence is also hard (there is in fact work in progress to prove this hypothesis). Given this hypothesis, we consider stability-preserving reductions to prove our hardness for stable k-means. Such reductions seem to be more fragile and intricate than standard L-reductions and may be of further use to demonstrate other stable optimization problems are hard to solve.
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 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".