arXiv research

Simple model outperforms neural networks on language understanding tasks.

Human inertial thinking schemes can be formed through learning, which are then applied to quickly solve similar problems later. However, when problems are significantly different, inertial thinking generally presents the solutions that are definitely imperfect. In such cases, people will apply creative thinking, such a…

State variables are easily the most subtle dimension of sequential decision problems. This is especially true in the context of active learning problems (bandit problems") where decisions affect what we observe and learn. We describe our canonical framework that models {\it any} sequential decision problem, and present…

Algorithm identifies Pareto front in multi-objective bandits efficiently.

For technology (like serious games) that aims to deliver interactive learning, it is important to address relevant mental experiences such as reflective thinking during problem solving. To facilitate research in this direction, we present the weDraw-1 Movement Dataset of body movement sensor data and reflective thinkin…

CausalGame benchmarks LLM agents' causal thinking in games.

This paper studies the problem of learning the conditional distribution of a high-dimensional output given an input, where the output and input may belong to two different domains, e.g., the output is a photo image and the input is a sketch image. We solve this problem by cooperative training of a fast thinking initial…

The seriousness of the current crisis urgently demands new economic thinking that breaks the austerity vs. deficit spending circle in economic policy. The core tenet of the paper is that the most important problems that natural and social science are facing today are inverse problems, and that a new approach that goes …

Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to perform better in similar future tasks. This paper investigates the counterfactual th…

Popular culture has contemplated societies of thinking machines for generations, envisioning futures from utopian to dystopian. These futures are, arguably, here now-we find ourselves at the doorstep of technology that can at least simulate the appearance of thinking, acting, and feeling. The real question is: now what…

A new reinforcement learning method for robots thinking and moving simultaneously.

Breiman's two cultures reconciled through blending statistical thinking.

The paper encourages Kleinian group thinking for higher rank Lie groups.

Bayesian approach helps update deep models without forgetting past data.

Causal thinking improves healthcare decisions from EHRs.

Simplified proof of a famous geometry result for students.

Model learns brevity by exposing to easy problems, improving efficiency without explicit length penalties.

Thinking LLMs struggle with stock prediction, especially as data complexity increases.

We present a general framework for training deep neural networks without backpropagation. This substantially decreases training time and also allows for construction of deep networks with many sorts of learners, including networks whose layers are defined by functions that are not easily differentiated, like decision t…

New algorithm trains neural nets on simple skills to learn complex tasks faster.

The use of the trading halts is a practice common to all markets. However, the advantages and the disadvantages of the measurements are regularly discussed. The partisans think that the trading suspensions or the price limits make it possible to the investors to have time to react to the new information. The detractors…

DGP learns speech recognition by modeling complex relationships between utterances.

Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans …

The success of deep neural networks has inspired many to wonder whether other learners could benefit from deep, layered architectures. We present a general framework called forward thinking for deep learning that generalizes the architectural flexibility and sophistication of deep neural networks while also allowing fo…

In the paper we give a compendium about theory of connection. We think that this compendium will be useful for young relativists.

New technique reduces language biases in large language models.

Breiman's paper sparked debate on the future of statistics and machine learning.

Can we manipulate multiple deep neural networks simultaneously?

Research suggests using deep learning for better recommendation systems.

A deep model learns to stop early based on variational stopping policy.

In this paper we study n-composition series of affine manifolds. One composition series are classified using gerbe theory. It is natural to think that n-composition series must be classified using n-gerbe theory. In the last section of this, we propose a notion of abelian n-gerbe theory

We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving complex tasks, typically in an unsupervised or weakly-supervised setting. DRNets exploit problem structure and prior knowledge by tightly combining logic and constraint reasoning with stochastic…

The paper converts metric bounds to distance function Hölder bounds and proves compactness theorems.

We argue that the present crisis and stalling economy continuing since 2007 are rooted in the delusionary belief in policies based on a "perpetual money machine" type of thinking. We document strong evidence that, since the early 1980s, consumption has been increasingly funded by smaller savings, booming financial prof…

Open geometry puzzles keep the author engaged.

We prove new results on existence of solutions for the prescribed gaussian curvature problem on the euclidean sphere S^2. Those results are achieved by relating this problem with the holomorphic triples theory on Riemann surfaces. We think this approach might be applied to study some other semi-linear elliptic equation…

Doctors often rely on their past experience in order to diagnose patients. For a doctor with enough experience, almost every patient would have similarities to key cases seen in the past, and each new patient could be viewed as a mixture of these key past cases. Because doctors often tend to reason this way, an efficie…

We discuss recently emerging applications of the state-of-art deep learning methods on optical microscopy and microscopic image reconstruction, which enable new transformations among different modes and modalities of microscopic imaging, driven entirely by image data. We believe that deep learning will fundamentally ch…

New method uses causal thinking to make AI fairer decisions.

We prove some general results about quasi-actions on trees and define Property (QFA), which is analogous to Serre's Property (FA), but in the coarse setting. This property is shown to hold for a class of groups, including $SL(n,\Z)$ for $n\geq 3$. We also give a way of thinking about Property (QFA) by breaking it down …

Undecidability proved for DG algebras problems.

In this short paper, we re-derive the Bochner formula for the Laplacian by considering local variations of volume. The derivation is rooted in the fact that the Laplacian of a function measures the volume variation along the flow of the gradient vector of the function. Possible extensions of this approach/technique are…

This is a survey on the geometry of warped products, without, or essentially with only soft, calculation. Somewhere in the paper, the goal was to give a synthetic account since existing approaches are rather analytic. Somewhere else, we have interpreted statements, especially by means of a physical terminology. This is…

We introduce Threatened Markov Decision Processes (TMDPs) as an extension of the classical Markov Decision Process framework for Reinforcement Learning (RL). TMDPs allow suporting a decision maker against potential opponents in a RL context. We also propose a level-k thinking scheme resulting in a novel learning approa…

The classical Brody's theorem asserts the equivalence between two notions of hyperbolicity for compact complex spaces, one named after Kobayashi and one expressed in terms of lack of non constant holomorphic entire functions (compactness is only used to prove the harder implication). We extend this theorem to Deligne-M…

Given an n-term L-infinity algebra L, we construct a Kan simplicial manifold which we think of as the 'Lie n-group' integrating L. This extends work of Getzler math.AT/0404003 . In the case of an ordinary Lie algebra, our construction gives the simplicial classifying space of the corresponding simply connect Lie group.…

Hybrid framework injects TSLM insights into GRLM for robust time-series reasoning.

Given any closed Kaehler manifold we define, following an idea by Eugenio Calabi, a Riemannian metric on the space of Kaehler metrics regarded as an infinite dimensional manifold. We prove several geometrical features of the resulting space, some of which we think were already known to Calabi. In particular, the space …