Pith Number

pith:TYFP47YC

pith:2026:TYFP47YCUZP2S3VOTW5JJBPB4J

not attested not anchored not stored refs resolved

State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives

Hoang-Son Tran, Pranav Gupta, R\'emi Bardenet, Subhroshekhar Ghosh

Wavelet-based DPPs on Euclidean space discretize to low-rank kernels that preserve superior variance reduction for minibatches on rough objectives.

arxiv:2605.13127 v1 · 2026-05-13 · stat.ML · cs.LG · math.PR

Open paper page JSON Open Graph Bundle Merged state What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{TYFP47YCUZP2S3VOTW5JJBPB4J}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

We propose new DPPs on the Euclidean space based on wavelets, with provably better accuracy guarantees than the best known rates. Second, we introduce a general method to convert such continuous DPPs into discrete kernels, which simultaneously preserves the desired variance decay and reveals a low-rank decomposition of the discrete kernel.

C2weakest assumption

The discretization procedure preserves the variance reduction properties of the continuous wavelet DPPs with only negligible degradation when applied to finite datasets, and that the low-rank structure remains exploitable without hidden computational costs.

C3one line summary

Wavelet DPP kernels deliver improved continuous variance reduction and a discretization procedure that preserves decay rates for discrete ML subsampling tasks including rough objectives.

References

299 extracted · 299 resolved · 16 Pith anchors

[1] Miramont, J. M. and Tan, K. A. and Mukherjee, S. S. and Bardenet, R. and Ghosh, S. , date-added =. arXiv preprint arXiv:2504.07720 , title =

[2] Miramont, J. M. and Auger, F. and Colominas, M. A. and Laurent, N. and Meignen, S. , date-added =. Signal Processing , title =

[3] Miramont, J. M. and Bardenet, R. and Chainais, P. and Auger, F. , booktitle =. Adaptive hyperparameter tuning for time-frequency algorithms based on the zeros of the spectrogram , year =

[4] Lacoste--Julien, S. and Husz. Approximate inference for the loss-calibrated. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS) , organization =

[5] Advances in Neural Information Processing Systems (NeurIPS) , title =

Receipt and verification

First computed	2026-05-18T03:08:57.855857Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9e0afe7f02a65fa96eae9dba9485e1e24e0a3c97a4edf33d682ca35143f11771

Aliases

arxiv: 2605.13127 · arxiv_version: 2605.13127v1 · doi: 10.48550/arxiv.2605.13127 · pith_short_12: TYFP47YCUZP2 · pith_short_16: TYFP47YCUZP2S3VO · pith_short_8: TYFP47YC

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/TYFP47YCUZP2S3VOTW5JJBPB4J \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 9e0afe7f02a65fa96eae9dba9485e1e24e0a3c97a4edf33d682ca35143f11771

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "37fa01c8078fcd21ad6b556a4f96d3ee0e352ad10bb897463c20c6a22e816d0d",
    "cross_cats_sorted": [
      "cs.LG",
      "math.PR"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "stat.ML",
    "submitted_at": "2026-05-13T07:54:37Z",
    "title_canon_sha256": "4c3b6fc00a830b55b9144ad0c1642d3ff24bfb8d45287df12715478db6a34303"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13127",
    "kind": "arxiv",
    "version": 1
  }
}