arXiv research

Global watermark for diffusion language models decouples detection from local contexts.

Tiled Squeeze-and-Excite improves channel attention with local spatial context.

NERS improves RL by sampling diverse transitions considering local and global contexts.

This paper learns graph node representations using global context prediction.

In this short note, a question of patching together globally hyperbolic manifolds is adressed which appeared in the context of the construction of Hadamard states.

In this work, we introduce the Global Planar Convolution module as a building-block for fully-convolutional networks that aggregates global information and, therefore, enhances the context perception capabilities of segmentation networks in the context of brain tumor segmentation. We implement two baseline architecture…

Improves medical note processing by training model on related concepts and global context.

A method for learning a context latent vector to improve generalization in model-based RL.

OCEAN infers online task identities from context variables.

We consider the problem of finding sufficient conditions for a locally Lipschitz mapping between Finsler manifolds to be a global homeomorphism. For this purpose, we develop the notion of Clarke generalized differential in this context and, using this, we obtain a version of the Hadamard integral condition for invertib…

Globally normalized neural sequence models are considered superior to their locally normalized equivalents because they may ameliorate the effects of label bias. However, when considering high-capacity neural parametrizations that condition on the whole input sequence, both model classes are theoretically equivalent in…

A long user history inevitably reflects the transitions of personal interests over time. The analyses on the user history require the robust sequential model to anticipate the transitions and the decays of user interests. The user history is often modeled by various RNN structures, but the RNN structures in the recomme…

Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms in order to make them more reliable. These models appear to store vast amounts of knowledge from their training data, and…

Researchers create a framework to value player actions in CSGO.

Study characterizes Einstein metrics in warped product spaces.

Interactions such as double negation in sentences and scene interactions in images are common forms of complex dependencies captured by state-of-the-art machine learning models. We propose Mahé, a novel approach to provide Model-agnostic hierarchical éxplanations of how powerful machine learning models, such as deep ne…

Example of spacetime with causal bubbling, splitting into timelike and spacelike parts.

Herd behavior is an important economic phenomenon, especially in the context of the recent financial crises. In this paper, herd behavior in global stock markets is investigated with a focus on intercontinental comparison. Since most existing herd behavior indices do not provide a comparative method, we propose a new h…

Geometric operators link solutions on different spacetimes.

Global homotopies upgrade classical map in differential geometry.

Transformers can handle endogeneity in linear regression using IV methods.

Deep neural networks have become commonplace in the domain of reinforcement learning, but are often expensive in terms of the number of parameters needed. While compressing deep neural networks has of late assumed great importance to overcome this drawback, little work has been done to address this problem in the conte…

The paper studies global invertibility of maps on Finsler manifolds.

Transformers learn linear models in-context without updates.

Quantum field theory uses Lorentzian bordisms to describe time evolution.

Develops a new framework to measure network connectedness across and within markets.

Transformers converge linearly to optimal models for Gaussian mixtures classification.

New method for private density estimation of high-dimensional Gaussian mixtures.

This paper is motivated by the non-linear stability problem for the expanding region of Kerr de Sitter cosmologies in the context of Einstein's equations with positive cosmological constant. We show that under dynamically realistic assumptions the conformal Weyl curvature of the spacetime decays towards future null inf…

Stochastic gradient descent (SGD) has been found to be surprisingly effective in training a variety of deep neural networks. However, there is still a lack of understanding on how and why SGD can train these complex networks towards a global minimum. In this study, we establish the convergence of SGD to a global minimu…

Proposes a topological framework to study modular invariants and related concepts.

Global stability bounds for matrix frames in phase retrieval problems.

We analyze the $K$-armed bandit problem where the reward for each arm is a noisy realization based on an observed context under mild nonparametric assumptions. We attain tight results for top-arm identification and a sublinear regret of $\widetilde{O}\Big(T^{\frac{1+D}{2+D}}\Big)$, where $D$ is the context dimension, f…

In contextual continuum-armed bandits, the contexts $x$ and the arms $y$ are both continuous and drawn from high-dimensional spaces. The payoff function to learn $f(x,y)$ does not have a particular parametric form. The literature has shown that for Lipschitz-continuous functions, the optimal regret is $\tilde{O}(T^{\fr…

Throughout economic history, the global economy has experienced recurring crises. The persistent recurrence of such economic crises calls for an understanding of their generic features rather than treating them as singular events. The global economic system is a highly complex system and can best be viewed in terms of …

The optimal transport problem is studied in the context of Lorentz-Finsler geometry. For globally hyperbolic Lorentz-Finsler spacetimes the first Kantorovich problem and the Monge problem are solved. Further the intermediate regularity of the transport paths is studied. These results generalize parts of Bertrand & Puel…

Transformer autoencoder learns musical style from performances.

Graph Signal Processing improves stock market volatility forecasting.

A new learning scheme improves model efficiency and performance.

New local MDI variable importances derived from global scores match Shapley values.

Proves stability of Minkowski space for specific initial data.

We prove an existence result for local and global G-structure preserving affine immersions between affine manifolds. Several examples are discussed in the context of Riemannian and semi-Riemannian geometry, including the case of isometric immersions into Lie groups endowed with a left-invariant metric, and the case of …

Hydra boosts efficiency for long-context reasoning in resource-constrained settings.

Expands Bredon's trick for applications in geometry and topology.

This paper, the third in a series, completes our description of all (radial) solutions on C* of the tt*-Toda equations, using a combination of methods from p.d.e., isomonodromic deformations (Riemann-Hilbert method), and loop groups. We place these global solutions into the broader context of solutions which are smooth…

Personalized models explain TB treatment outcomes considering patient context.

Develops methods to analyze feature-outcome associations in subpopulations.

The study identifies assets with local balance deviating from global balance to mitigate financial risk.