ACM Symposium on Theory of Computing
PulseAugur coverage of ACM Symposium on Theory of Computing — every cluster mentioning ACM Symposium on Theory of Computing across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New theory tightens bounds on list replicability in PAC learning
Researchers have established a new upper bound for list replicability in the PAC learning framework, significantly improving upon previous results. The study demonstrates that for concept classes with a Littlestone dime…
-
New dynamic Haussler lemma offers sharp bounds for real-valued classes
This paper introduces a sharp global dynamic analogue to Haussler's covering lemma, extending it to bounded real-valued classes under normalized $\ell_p$ distance for $1 \le p < \infty$. The research provides a global d…
-
New algorithm achieves nearly linear private learning for Littlestone classes
Researchers have developed a new algorithm for differentially private learning, significantly improving the sample complexity for learning Littlestone classes. The new bound is nearly linear, $O(d\log d)$, a substantial…
-
New research explores computational and statistical hardness of calibration distance
Researchers have investigated the computational and statistical challenges associated with calibration distance, a key metric for evaluating probabilistic predictors. They developed an efficient algorithm for exact comp…
-
Google launches Deep Review AI for technical document verification
Google Research has publicly launched Deep Review, an AI system designed to provide rigorous technical verification and feedback on complex documents. Initially developed as the Paper Assistant Tool (PAT) to aid in acad…
-
New $γ$-VC Dimension Parameter Analyzed for Weak Learner Boosting
This paper introduces and analyzes the $γ$-VC dimension, a parameter that characterizes the sample complexity for converting weak hypotheses into accurate predictors. The research refines the relationship between the tr…
-
Google's Stellar Colosseum tackles long-horizon math proofs with Gemini models
Google Research has developed a novel multi-agent system called Stellar Colosseum, designed to tackle long-horizon tasks, particularly in mathematical proofs. This system operates in stages, generating candidate solutio…
-
ReLU networks can represent max function with fewer layers
Researchers have demonstrated that the maximum of n real numbers can be precisely represented by a ReLU network with two hidden layers for any n up to 10. This is achieved by translating the problem into exact rational …
-
Google AI reviews 10,000 papers, catching 34% more errors
Google has developed an AI system capable of performing peer reviews for scientific papers, successfully processing approximately 10,000 submissions for the ICML and STOC conferences. A formal research paper detailing t…
-
Google's Paper Assistant Tool Automates Scientific Review
Google has developed the Paper Assistant Tool (PAT), an AI framework designed to aid in the scientific review process. PAT analyzes full manuscripts to check theoretical results, validate experiments, and identify poten…
-
Google Gemini tool offers automated feedback for scientific papers
Google Research has developed an experimental AI tool called the Paper Assistant Tool (PAT), which utilizes an advanced version of Gemini 2.5 Deep Think to provide automated feedback on theoretical computer science pape…