Adversarial Bandit Optimization with Globally Bounded Perturbations to Linear Losses

Adversarial Bandit Optimization with Globally Bounded Perturbations to Linear Losses | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/adversarial-bandit-optimization-with-globally-bounded-perturbations-to-linear-losses

stale

Proof freshness: stale
Proof status: unverified
Display score: 2/10
Last proof check: 2026-03-30
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 23
Source count: 3
Coverage: 50%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

Canonical ID adversarial-bandit-optimization-with-globally-bounded-perturbations-to-linear-losses | Route /signal-canvas/adversarial-bandit-optimization-with-globally-bounded-perturbations-to-linear-losses

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/adversarial-bandit-optimization-with-globally-bounded-perturbations-to-linear-losses

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "adversarial-bandit-optimization-with-globally-bounded-perturbations-to-linear-losses",
    "query_text": "Summarize Adversarial Bandit Optimization with Globally Bounded Perturbations to Linear Losses"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "Adversarial Bandit Optimization with Globally Bounded Perturbations to Linear Losses",
  "normalized_query": "2603.26066",
  "route": "/signal-canvas/adversarial-bandit-optimization-with-globally-bounded-perturbations-to-linear-losses",
  "paper_ref": "adversarial-bandit-optimization-with-globally-bounded-perturbations-to-linear-losses",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 7

References: 23

Proof: Verification pending

Freshness state: computing

Source paper: Adversarial Bandit Optimization with Globally Bounded Perturbations to Linear Losses

PDF: https://arxiv.org/pdf/2603.26066v1

Source count: 3

Coverage: 50%

Last proof check: 2026-03-30T22:00:28.241Z

Signal Canvas receipt window

Not build-ready: Adversarial Bandit Optimization with Globally Bounded Perturbations to Linear Losses

/buildability/adversarial-bandit-optimization-with-globally-bounded-perturbations-to-linear-losses

Ignoreblocked

Subject: Adversarial Bandit Optimization with Globally Bounded Perturbations to Linear Losses

Verdict

Ignore

Verdict is Ignore because current viability and proof state do not clear the buildability gate.

Preparing verified analysis

GitHub Code Pulse

No public code linked for this paper yet.

Claim map

Strong 7Mixed 0Weak 0

Evidencepartial
The algorithm maintains a sequence {xt}T t=1⊂K , which is updated according to xt+1 = arg min x∈K { η ∑t τ =1 g⊤ τ x +R(x) }
Implicationpartial
This is a direct description of the SCRiBLe algorithm's update rule, explicitly stated in the text.
Verificationpartial
partial
Evidencepartial
SCRiBLe utilizes a ν-self-concordant barrier R, which always exists on the action setK.
Implicationpartial
This statement clearly defines a property of the SCRiBLe algorithm and its reliance on a specific type of barrier function.
Verificationpartial
partial
Evidencepartial
Under this model, we establish both expected and high-probability regret guarantees.
Implicationpartial
This is a primary result explicitly stated in the abstract and reinforced by the mention of Lemma 9's role in deriving these guarantees.
Verificationpartial
partial
Evidencepartial
As a special case of our analysis, we recover an improved high-probability regret bound for classical bandit linear optimization, which corresponds to the setting without perturbations.
Implicationpartial
This is a specific outcome of the general analysis, highlighted in the abstract as a notable consequence.
Verificationpartial
partial
Evidencepartial
We further complement our upper bounds by proving a lower bound on the expected regret.
Implicationpartial
This is a key theoretical contribution mentioned in the abstract, indicating a complete picture of the regret bounds.
Verificationpartial
partial
Evidencepartial
The lemmas presented above collectively lead to Lemma 9, which constitutes a key technical result of this paper. In particular, it establishes a bound on ∑T t=1 θ⊤ t xt−∑T t=1 θ⊤ t x∗
Implicationpartial
The text explicitly labels Lemma 9 as a 'key technical result' and describes its specific mathematical contribution.
Verificationpartial
partial
Evidencepartial
Theorem 12 For any horizon T ≥ 1 and any player, there exists an adversary generating a C-approximately linear function sequence such that the regr et is at least 2C.
Implicationpartial
This is a specific lower bound result presented as Theorem 12, with clear conditions and outcome.
Verificationpartial
partial

Author intelligence and commercialization panels stay hidden until the proof receipt is verified, cites at least 3 references, includes at least 2 sources, and clears 50% coverage. The paper narrative and citation surfaces remain public while verification is pending.

Adversarial Bandit Optimization with Globally Bounded Perturbations to Linear Losses

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface