跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1085新增论文
+884其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 06:59各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 08:33 — 2026-11-19 08:33(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59库内论文最新更新时间:2026-11-18 08:00

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

26,871 已收录论文22,375 AI 相关8,156 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 4 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
新论文 · v1arXiv:2611.09747

对抗性调度器下的争用解决

Contention Resolution Against an Adversarial Scheduler

Michael A. Bender, Martín Farach-Colton, Andrew Krapivin, Pritom Kundu, John Kuszmaul, Margaret Kuszmaul, William Kuszmaul, Jingxun Liang

AI 速读 基于摘要

研究在对抗性调度器可任意决定每步哪些玩家参与的新模型下,争用解决协议能达到的效率上界与下界。

cs.DS

查看原文摘要

In the classical contention-resolution problem, a set of players share a broadcast channel, and a player succeeds in a given time step if it is the only player to broadcast during that step. Implicit in the classical problem is the assumption that every player is free to act on every step: once a player arrives, it participates until it succeeds. We study what happens when that assumption is removed. In our model, an adversarial \emph{scheduler} decides, on each step, which subset of the players gets scheduled to participate in the step. An unscheduled player simply sleeps through the step. We measure a protocol by its \emph{efficiency}: the number of players divided by the expected number of steps in which at least one player was active. Our first result says that, so long as the players are given access to a global clock and to shared randomness, they can achieve efficiency $Ω(1/\log n)$. The players are able to achieve this bound without requiring any channel feedback, and even if the adversarial scheduler is adaptive. We also give a matching lower bound of $O(1 / \log n)$, which holds even with channel feedback, and even for an oblivious scheduler. Our upper bounds all require the players to have access to a shared global clock and to shared randomness. Our final result says that this type of implicit shared state is necessary. If the players have neither a global clock nor shared randomness, then no protocol can achieve efficiency better than $O(\log n / n)$; and this holds even if the other aspects of the problem are designed to be as favorable for the players as possible (the channel gives ternary feedback and the adversary is oblivious).

新论文 · v1arXiv:2611.05235

Catalan 哈希:面向变长元素的高效线性探测

Catalan Hashing: Efficient Linear Probing for Variable-Length Items

Alex Conway, Hanna Komlós, William Kuszmaul

AI 速读 基于摘要

提出 Catalan hashing,在存储任意长度元素的线性探测哈希表中,将扫描代价控制在接近单位长度情形的量级。

cs.DS

查看原文摘要

A defining feature of the linear-probing hash table is its spatial locality: at load factor $1 - \varepsilon$, the hash table can be implemented so that each operation scans a single contiguous region of expected size $O(1/\varepsilon)$ (this is known as the \emph{scan cost}). This guarantee, however, relies on all items having unit size. In this paper, we ask whether it is possible to achieve a similar guarantee, but in a hash table that stores items of arbitrary lengths $|x| \ge 1$. The main result of the paper is a new hash table called \emph{Catalan hashing}, which supports amortized expected scan cost $O(|x|/\varepsilon)$ for positive queries, $O(1/\varepsilon)$ for negative queries, and $O(|x|\varepsilon^{-1}\log^{1+δ}|x|)$ for insertions/deletions, for any constant $δ> 0$. As a corollary, we obtain the same bounds in the cache-oblivious model, with a scan cost of $S$ translating to $1 + O(S/B)$ I/Os. Along the way, we introduce several high-level techniques that may be of independent interest; this includes a novel way of using erasure codes in order to perform write optimization within a hash table, and a connection to scheduling that allows us to place elements in a way which avoids clustering at high load factors.

新论文 · v1arXiv:2611.04186

Incremental Open Addressing Has No Time-Space Tradeoff

Martín Farach-Colton, Andrew Krapivin, William Kuszmaul

原文摘要

In this paper, we show that there is no time-space tradeoff in incremental open addressing: there is an incremental open-addressed hash table that supports $O(1)$ worst-case expected time insertions, positive queries, and negative queries, at any load factor (even load factor $1$). As an intermediate result, we also revisit the problem of constructing an incremental open-addressed hash table that does not perform reordering (does not move elements around over time). In this setting, we show that it is possible to get $O(1)$ amortized expected positive query time together with $O(1)$ worst-case expected insertion time, a combination that was not previously known to be possible.

cs.DS

版本更新 · v2arXiv:2605.06014

Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven

Ran Ben-Basat, William Kuszmaul, Michael Mitzenmacher, Amit Portnoy, Shay Vargaftik

原文摘要

Uniform random rotations (URRs) are a common preprocessing step in modern quantization approaches used for gradient compression, inference acceleration, KV-cache compression, model weight quantization, and approximate nearest-neighbor search in vector databases. In practice, URRs are often replaced by randomized Hadamard transforms (RHTs), which preserve orthogonality while admitting fast implementations. The remaining issue is the performance for worst-case inputs. With a URR, each coordinate is distributed as a shifted beta distribution, which converges to a Gaussian distribution in high dimensions. Generally, one RHT is not suitable in the worst case, as individual coordinates can be far from these distributions. We show that after composing two RHTs on any $d$-sized input vector, the marginal distribution of every fixed coordinate of the normalized rotated vector is within $O(d^{-1/2})$ of a standard Gaussian both in Kolmogorov distance and in $1$-Wasserstein distance. We then plug these bounds into the analyses of modern compression schemes, namely DRIVE and QUIC-FL, and show that two RHTs achieve performance that asymptotically matches URRs. However, while two RHTs suffice for scalar quantization, they may be insufficient for Vector Quantization (VQ), which depends on the joint distribution across fixed-size blocks of coordinates (as opposed to only marginal distribution convergence for single coordinates). We prove that a composition of three RHTs leads to decaying coordinate covariance. This ensures that any fixed, bounded, multi-dimensional VQ codebook optimized for URRs has the same expected error when using three RHTs, up to an additive term that vanishes with the dimension. Finally, because practical inputs are rarely adversarial, we propose a linear-time $O(d)$ check on the input's moments to dynamically adapt the number of RHTs used at runtime to improve performance.

cs.LG · cs.AI · cs.DS · cs.NI