source/challenge_target_snapshot.json

{
  "anchored_claims": [
    "Theorem 1 establishes an Õ(d^{3/2}√V_T) regret bound for one-point bandit convex optimization with gradient variation V_T, improving the dimension dependence over Chiang et al. (2013)'s O(d^3√V_T) bound (Theorem 1, Section 3.1).",
    "Theorem 2 gives an O((d/λ) log V_T) regret bound for λ-strongly convex functions, improving the prior O((d^2/λ) log V_T) bound by a factor of d (Theorem 2, Section 3.2).",
    "Theorem 3 provides O(√(dW_T) + d) regret for linear functions and O(d√W_T + d) regret for convex functions in terms of the gradient variance W_T (Theorem 3, Section 3.3).",
    "Theorem 4 delivers O(√(dF_T) + d) regret bounds for linear and convex functions using the small-loss quantity F_T (Theorem 4, Section 3.3).",
    "Section 4 presents the first gradient-variation regret bound for one-point bandit linear optimization over hyper-rectangular domains (Section 4).",
    "Table 1 summarizes the dimension-dependence improvements across gradient-variation, gradient-variance, and small-loss metrics for linear, convex, and strongly convex function classes relative to prior best-known results (Table 1)."
  ],
  "author_space_count": 64,
  "base_claims": [
    "Improves dimension dependence for both convex and strongly convex functions in Bandit Convex Optimization compared to best known results.",
    "First gradient-variation bounds for one-point bandit linear optimization over hyper-rectangular domains.",
    "First gradient-variation dynamic and universal regret bounds for two-point Bandit Convex Optimization."
  ],
  "bucket_url": "https://huggingface.co/buckets/neonforestmist/improved-dimension-bco-gradient-variation-repro-artifacts",
  "captured_utc": "2026-07-18T21:17:07+00:00",
  "checks": {
    "exact_six_anchored_claims": true,
    "exact_six_ceiling": true,
    "exact_three_base_claims": true,
    "leaderboard_present": true,
    "no_prior_neon_verdict": true,
    "official_index_identity": true,
    "official_pdf": true,
    "official_source": true,
    "tag_absent": true,
    "target_absent": true
  },
  "checks_passed": 10,
  "checks_total": 10,
  "failed_checks": [],
  "gpu_used": false,
  "mps_used": false,
  "neon_verdicts": [],
  "official_base_ceiling": 6,
  "orid_verdicts": {},
  "paper": {
    "alphaxiv": "2602.04761",
    "area": "Theory",
    "arxiv": "2602.04761",
    "authors": [
      "Hang Yu",
      "Yu-Hu Yan",
      "Peng Zhao"
    ],
    "hf": "",
    "i": 20598,
    "insts": [],
    "or": "https://openreview.net/forum?id=X8evkEdMxb",
    "orid": "X8evkEdMxb",
    "pid": "20598",
    "spot": true,
    "sub": "Online Learning And Bandits",
    "title": "Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variation",
    "type": "Poster",
    "vs": "https://icml.cc/virtual/2026/poster/20598"
  },
  "pinned_revisions": {
    "challenge_dataset": "43305cce7d7fc4f5c3f50a79f6d97bf5d2185a77",
    "challenge_space": "6660ac45d121e2b9e9a7a4d9b675d8e66ead8785",
    "verdict_dataset": "c8027f1c1ffd4c6ac66554c450d4a0fe0305732b"
  },
  "publication_lock": "REMOTE WRITE ONLY AFTER COORDINATOR ASSIGNS A ROLLING SLOT",
  "remote_write_attempted": false,
  "required_tags": [
    "icml2026-repro",
    "paper-X8evkEdMxb"
  ],
  "response_sha256": {
    "anchored_pinned": "eb3f2d878646ca5c40da121741a613c1f9e1e10c14845f373db107e74a4ef439",
    "anchored_static": "eb3f2d878646ca5c40da121741a613c1f9e1e10c14845f373db107e74a4ef439",
    "author_spaces": "2c59b48828adeb74018ce1cf98735b1d799ebb4b741216176c845f6cfec9d2c8",
    "challenge_dataset_meta": "ff1bcac415ab1b2b4e6b552f7a05aee588080e8ddd70f6d1e638a05ede98d289",
    "challenge_space_meta": "64019ad23db80403c0a3066acf51f9cdc2273a09451f7fe8620828234238856d",
    "claims_pinned": "af5ab2d62f786ae36861957cbd08b4188f6d4c86e67152becc661a9c5bbb9d57",
    "claims_static": "af5ab2d62f786ae36861957cbd08b4188f6d4c86e67152becc661a9c5bbb9d57",
    "leaderboard_html": "76e3d194bf15827e15790b055b939c6af7fb24cb1278f8b2ee813132d3cf4523",
    "leaderboard_js": "30bd264df8d3128b9fff248a277e41445fd23949b69280c16162d429591b382c",
    "official_index": "cc56683faf8b20730d40c8821eaecb737125c510d83474793ca5e9410b7e9a6b",
    "official_verdicts": "95ec4be3aa5a9598e8d73aab5f442d8a7d63850fa9543b1ff9d34876dc927f18",
    "verdict_dataset_meta": "bad2cd398e3e096cb9919e6e8a407cb6663d418bc0184d89957a6f6f47a5fcca"
  },
  "schema_version": 1,
  "status": "PASS",
  "tag_matches": [],
  "target_matches": [],
  "target_space": "neonforestmist/improved-dimension-bco-gradient-variation-repro"
}