max@K
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Exponential Quantum Space Advantage for Approximating Max-$k$SAT in the Streaming Setting
Announce Type: new Abstract: In this paper, we give a one-pass quantum streaming algorithm for Max-$k$SAT that uses $\operatorname{polylog}(n)$ space and achieves a $0.7172$-approximation on instances with $n$ variables. In contrast, prior work by Chou, Golovnev, and Velusamy (FOCS 2020) implies that achieving an approximation ratio better than $\sqrt{2}/2 \approx 0.7071$ for Max-$k$SAT requires $\Omega(\sqrt{n})$ space for any classical streaming algorithm. Therefore, it yields an...
On Advantage Estimates for Max@K Policy Gradients
arXiv:2606.06080v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards is widely used for post-training reasoning models, but sparse outcome rewards make exploration difficult. A complementary approach is to optimize inference-time objectives such as pass@K and max@K directly, yet existing policy-gradient estimators for these objectives use different signals, baselines, and normalizations, making their relationships unclear. We study this issue through baseline design...
Finite-Time Regret Analysis of Retry-Aware Bandits
Announce Type: replace Abstract: We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@$k$ and max@$k$. Given a posterior over arm values, ReMax chooses a sampling distribution that maximizes the posterior expected maximum reward over $M$ virtual draws. Although this objective was introduced in reinforcement learning as an exploration mechanism under uncertainty, its regret properties in bandit problems...
Retry Policy Gradients in Continuous Action Spaces
arXiv:2606.05888v1 Announce Type: new Abstract: Retry-based objectives such as pass@K and max@K optimize the best return obtained from multiple sampled trajectories, and recent work has shown that they can promote exploration without explicit exploration bonuses. In discrete action spaces, ReMax was shown to do so by adapting to return uncertainty. In this work, we introduce pathwise derivative estimators for retry objectives and use them to extend ReMax to continuous action spaces.
Almost covering all the layers of hypercube with multiplicities
Announce Type: replace-cross Abstract: Given a hypercube $\mathcal{Q}^{n} := \{0,1\}^{n}$ in $\mathbb{R}^{n}$ and $k \in \{0, \dots, n\}$, the $k$-th layer $\mathcal{Q}^{n}_{k}$ of $\mathcal{Q}^{n}$ denotes the set of all points in $\mathcal{Q}^{n}$ whose coordinates contain exactly $k$ many ones. For a fixed $t \in \mathbb{N}$ and $k \in \{0, \dots, n\}$, let $P \in \mathbb{R}\left[x_{1}, \dots, x_{n}\right]$ be a polynomial that has zeroes of multiplicity at least $t$ at all points of...
Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective
Announce Type: replace Abstract: Generative Modeling via Drifting~\citep{deng2026drifting} has recently achieved state-of-the-art one-step image generation through a kernel-based drift operator, yet its success is largely empirical and its theoretical foundations remain poorly understood. We observe that \emph{under a Gaussian kernel, the drift operator is exactly a score difference on smoothed distributions}. This answers three questions left open in the original work: (1) whether a...
Proven Advantage of Multiobjective Evolutionary Algorithms for Problems with Different Degrees of Conflict
arXiv:2408.04207v3 Announce Type: replace Abstract: The field of multiobjective evolutionary algorithms (MOEAs) often emphasizes its popularity for optimization problems with conflicting objectives. However, it is still theoretically unknown how MOEAs perform compared with typical approaches outside this field. This paper conducts such a systematic theoretical comparison on problem classes with different degrees of conflict.
AMP: A Vendor-Neutral Wire Format for Agent Memory Operations
arXiv:2606.01138v1 Announce Type: new Abstract: Agent-memory frameworks - mem0, Letta/MemGPT, Cognee, Zep/Graphiti, MemoryOS, MemTensor - each ship their own SDK, storage layout, and operational vocabulary. There is no shared wire format: every integration is bespoke, every migration rebuilds memory from scratch, and no framework ships a governance surface that lets a human review writes before they enter long-term storage. We present memorywire, a JSON-Schema 2020-12 wire format for five...
memorywire: A Vendor-Neutral Wire Format for Agent Memory Operations
arXiv:2606.01138v2 Announce Type: replace Abstract: Agent-memory frameworks -- mem0, Letta/MemGPT, Cognee, Zep/Graphiti, MemoryOS, MemTensor -- each ship their own SDK, storage layout, and operational vocabulary. There is no shared wire format: every integration is bespoke, every migration rebuilds memory from scratch, and no framework ships a governance surface that lets a human review writes before they enter long-term storage. We present memorywire, a JSON-Schema 2020-12 wire format for...
$O(n +f(k))$: Truly Linear FPT
Announce Type: new Abstract: Parameterized complexity has always been concerned with practical computing: by confining combinatorial explosion to a secondary parameter $k$, one can uncover why and how many NP-hard problems are effectively tackled in practice. Today, however, the scale of data has changed: scientists study Big Data, which is so large that even quadratic dependence in the total input size $n$ is unaffordable. Therefore, what constitutes a practical algorithm has also changed.