English
Related papers

Related papers: On a Conjecture Regarding the Adam Optimizer

200 papers

Researchers have started using LLM agents in place of human subjects in behavioural and political-science experiments, often as a cheaper substitute for laboratory pools. The substitution does not hold up in strategic settings: humans and…

General Economics · Economics 2026-05-27 Po Han Teo

Humans rely more and more on systems with AI components. The AI community typically treats human inputs as a given and optimizes AI models only. This thinking is one-sided and it neglects the fact that humans can learn, too. In this work,…

Human-Computer Interaction · Computer Science 2020-09-22 Johannes Schneider

Human beings are considered as the most intelligent species on Earth. The ability to think, to create, to innovate, are the key elements which make humans superior over other existing species on Earth. Machines lack all those elements,…

Other Computer Science · Computer Science 2019-07-11 Ravin Kumar

We prove a conjecture of Kurdyka stating that every arc-symmetric semialgebraic set is precisely the zero locus of an arc-analytic semialgebraic function. This implies, in particular, that arc-symmetric semialgebraic sets are in one-to-one…

Algebraic Geometry · Mathematics 2017-09-29 Janusz Adamus , Hadi Seyedinejad

Most systems and learning algorithms optimize average performance or average loss -- one reason being computational complexity. However, many objectives of practical interest are more complex than simply average loss. This arises, for…

Machine Learning · Computer Science 2018-06-05 Daniel Alabi , Nicole Immorlica , Adam Tauman Kalai

Training language models becomes increasingly expensive with scale, prompting numerous attempts to improve optimization efficiency. Despite these efforts, the Adam optimizer remains the most widely used, due to a prevailing view that it is…

Machine Learning · Computer Science 2025-03-03 Rosie Zhao , Depen Morwani , David Brandfonbrener , Nikhil Vyas , Sham Kakade

Mathematical theorems are human knowledge able to be accumulated in the form of symbolic representation, and proving theorems has been considered intelligent behavior. Based on the BHK interpretation and the Curry-Howard isomorphism, proof…

Neural and Evolutionary Computing · Computer Science 2016-04-18 Li-An Yang , Jui-Pin Liu , Chao-Hong Chen , Ying-ping Chen

This paper offers a concise, 60-year synthesis of human-AI collaboration, from Licklider's ``man-computer symbiosis" (AI as colleague) and Engelbart's ``augmenting human intellect" (AI as tool) to contemporary poles: Human-Centered AI's…

Human-Computer Interaction · Computer Science 2026-01-13 Richard Jiarui Tong

The Alternating Direction Method of Multipliers (ADMM) has gained a lot of attention for solving large-scale and objective-separable constrained optimization. However, the two-block variable structure of the ADMM still limits the practical…

Optimization and Control · Mathematics 2020-03-24 Kresimir Mihic , Mingxi Zhu , Yinyu Ye

This paper proposes a research direction to advance AI which draws inspiration from cognitive theories of human decision making. The premise is that if we gain insights about the causes of some human capabilities that are still lacking in…

This work uses genetic programming to explore the space of continuous optimisers, with the goal of discovering novel ways of doing optimisation. In order to keep the search space broad, the optimisers are evolved from scratch using Push, a…

Neural and Evolutionary Computing · Computer Science 2021-11-16 Michael A. Lones

Transformers have recently been shown to be capable of reliably performing logical reasoning over facts and rules expressed in natural language, but abductive reasoning - inference to the best explanation of an unexpected observation - has…

Computation and Language · Computer Science 2022-03-24 Nathan Young , Qiming Bao , Joshua Bensemann , Michael Witbrock

Recent work in the behavioural sciences has begun to overturn the long-held belief that human decision making is irrational, suboptimal and subject to biases. This turn to the rational suggests that human decision making may be a better…

Machine Learning · Computer Science 2020-06-09 Haiyang Chen , Hyung Jin Chang , Andrew Howes

This paper is on Bayesian inference for parametric statistical models that are defined by a stochastic simulator which specifies how data is generated. Exact sampling is then possible but evaluating the likelihood function is typically…

Machine Learning · Statistics 2020-03-02 Borislav Ikonomov , Michael U. Gutmann

In this research, an optimal algorithm for the Collatz conjecture is presented. Properties such as the convergence of the algorithm and an equation that relates the algorithm to the classical Collatz conjecture are obtained. It is validated…

General Mathematics · Mathematics 2024-07-23 Juan Carlos Riano-Rojas

Human computation or crowdsourcing involves joint inference of the ground-truth-answers and the worker-abilities by optimizing an objective function, for instance, by maximizing the data likelihood based on an assumed underlying model. A…

Machine Learning · Statistics 2014-11-24 Nihar B. Shah , Dengyong Zhou

The rapid scaling of large language models (LLMs) has made low-precision training essential for reducing memory, improving efficiency, and enabling larger models and datasets. Existing convergence theories for adaptive optimizers, however,…

Machine Learning · Computer Science 2026-03-03 Xuan Tang , Jichu Li , Difan Zou

The question of how humans solve problem has been addressed extensively. However, the direct study of the effectiveness of this process seems to be overlooked. In this paper, we address the issue of the effectiveness of human problem…

Artificial Intelligence · Computer Science 2018-04-26 Frantisek Duris

This note serves two purposes. Firstly, we construct a counterexample to show that the statement on the convergence of the alternating direction method of multipliers (ADMM) for solving linearly constrained convex optimization problems in a…

Optimization and Control · Mathematics 2020-06-09 Liang Chen , Defeng Sun , Kim-Chuan Toh

A landmark negative result of Long and Servedio established a worst-case spectacular failure of a supervised learning trio (loss, algorithm, model) otherwise praised for its high precision machinery. Hundreds of papers followed up on the…

Machine Learning · Computer Science 2022-05-26 Yishay Mansour , Richard Nock , Robert C. Williamson
‹ Prev 1 8 9 10 Next ›