Note: Causality can be encoded without strict time function choice.
problem Global encoding of causality under natural conditions.
method Observation of weakening causality assumptions in existing results.
result Causality can be encoded without strict time function choice.
ETC improves Transformer models for long and structured inputs.
problem Scaling input length and encoding structured inputs in Transformers.
method Introduces global-local attention, relative position encodings, and CPC pre-training.
result Achieves state-of-the-art results on four natural language datasets.
GAMLA learns manifold structures with auto-encoding for global insights.
problem Limited global insight and lack of interpretable analytical descriptions in manifold learning.
method Two-round auto-encoding process to derive character and complementary representations.
result GAMLA provides global and analytical descriptions of smooth manifolds.
Deep learning models have shown state-of-the-art performance in many inverse reconstruction problems. However, it is not well understood what properties of the latent representation may improve the generalization ability of the network. Furthermore, limited models have been presented for inverse reconstructions over ti…
When doing representation learning on data that lives on a known non-trivial manifold embedded in high dimensional space, it is natural to desire the encoder to be homeomorphic when restricted to the manifold, so that it is bijective and continuous with a continuous inverse. Using topological arguments, we show that wh…
We consider the problem of learning high-level controls over the global structure of generated sequences, particularly in the context of symbolic music generation with complex language models. In this work, we present the Transformer autoencoder, which aggregates encodings of the input data across time to obtain a glob…
iREPA shows spatial structure, not global semantic, drives generation performance in REPA.
problem Understanding what aspect of the target representation matters for generation.
method Empirical analysis of 27 vision encoders, two modifications to REPA.
result Spatial structure, not global semantic, drives generation performance.
Paper proposes LCP for structural encodings, outperforming existing methods.
problem Improving Graph Neural Networks performance through effective structural encodings.
method Geometric perspective, Local Curvature Profiles (LCP) for structural encodings, combining with global positional encodings, comparing with rewiring techniques.
result LCP significantly outperforms existing structural encodings and combining LCP with global positional encodings improves performance.
Improved OOD detection across various shifts using multi-encoder fusion of RDMs.
problem Out-of-distribution detection across multiple types of distribution shifts.
method Statistical identification of encoder sensitivity, EncMin2L fusion, and Tippett minimum combination.
result Achieves AUROC ≥ 0.94 across four shift types, outperforming state-of-the-art detectors.
Proves globally hyperbolic spacetimes via null distance completeness.
problem No Hopf-Rinow Theorem in Lorentzian Geometry.
method Observation of null distances and their behavior with time functions.
result Proves globally hyperbolic spacetimes via null distance completeness.
Recently, GAIL framework and various variants have shown remarkable possibilities for solving practical MDP problems. However, detailed researches of low-level, and high-dimensional state input in this framework, such as image sequences, has not been conducted. Furthermore, the cost function learned in the traditional …
QuantNet learns global market trends to improve trading strategies.
problem Developing global trading strategies from multiple markets' data.
method QuantNet integrates transfer and meta-learning to learn market-agnostic trends and market-specific strategies.
result QuantNet outperformed top baseline strategies by 51% Sharpe and 69% Calmar ratios.
A new model decouples global and local image representations without supervision.
problem Learning decoupled global and local image representations without supervision.
method Variational auto-encoding framework with invertible generative flow.
result The model effectively learns decoupled representations of images.
Conformer encoder reverses sequence in time dimension, affecting decoder training.
problem Reversal of sequence in Conformer encoder impacts decoder training.
method Analyzed initial behavior of decoder cross-attention and proposed methods to avoid flipping.
result Self-attention module of Conformer starts dominating, allowing only reversed information to pass.
Randomized positional encodings boost transformer performance on longer sequences.
problem Transformers struggle with generalizing to sequences of arbitrary length.
method Introduced randomized positional encodings that simulate longer sequences and randomly select positions.
result Randomized positional encodings increase test accuracy by 12.0% on average for sequences of unseen length.
We give a topological model for a polynomial map from $\C^n$ to $\C$ in the neighborhood of a fiber with isolated singularities. This is motivated out of the ``unfolding of links'' described earlier by the first author and Lee Rudolph. The topological model gives a useful encoding of the local and global monodromy for …
Centroid-Encoder reduces high-dimensional data for better visualization.
problem Visualizing high-dimensional data efficiently and accurately.
method Centroid-Encoder integrates label information to keep similar objects close in reduced space.
result Centroid-Encoder outperforms other techniques in visualizing high-dimensional data.
Paper proposes a new Autoencoder for robustly encoding white matter streamlines.
problem Limited Autoencoder architectures ignore global streamline geometry and lack interpretability.
method Introduces Differentiable Vector Quantized Variational Autoencoder (D-VQ-VAE) for entire streamline bundles.
result Demonstrates superior performance in encoding and synthesis compared to state-of-the-art Autoencoders.
We introduce a simple recurrent variational auto-encoder architecture that significantly improves image modeling. The system represents the state-of-the-art in latent variable models for both the ImageNet and Omniglot datasets. We show that it naturally separates global conceptual information from lower level details, …
Generative adversarial networks (GANs) have demonstrated to be successful at generating realistic real-world images. In this paper we compare various GAN techniques, both supervised and unsupervised. The effects on training stability of different objective functions are compared. We add an encoder to the network, makin…
An essential aspect of texture analysis is the extraction of features that describe the distribution of values in local, spatial regions. We present a localized histogram layer for artificial neural networks. Instead of computing global histograms as done previously, the proposed histogram layer directly computes the l…
Quantum field theory uses Lorentzian bordisms to describe time evolution.
problem Describing the time evolution of quantum field theories.
method Defines a functorial field theory on Lorentzian bordism pseudo-category.
result Lorentzian bordisms naturally arise in algebraic quantum field theory.
Automatic summarisation is a popular approach to reduce a document to its main arguments. Recent research in the area has focused on neural approaches to summarisation, which can be very data-hungry. However, few large datasets exist and none for the traditionally popular domain of scientific publications, which opens …
In many important machine learning applications, the training distribution used to learn a probabilistic classifier differs from the testing distribution on which the classifier will be used to make predictions. Traditional methods correct the distribution shift by reweighting the training data with the ratio of the de…
Prove a global shadow lemma for Patterson-Sullivan measures associated with relatively Morse subgroups in higher-rank semisimple Lie groups.
problem Prove a global shadow lemma for Patterson-Sullivan measures associated with relatively Morse subgroups in higher-rank semisimple Lie groups.
method Prove a global shadow lemma for Patterson-Sullivan measures associated with relatively Morse subgroups in higher-rank semisimple Lie groups.
result Prove a global shadow lemma for Patterson-Sullivan measures associated with relatively Morse subgroups in higher-rank semisimple Lie groups.
New method learns to encode predictions within interpretations, improving evaluation.
problem Need for interpretable machine learning, but existing methods are slow or lack fidelity.
method Amortized explanation methods that learn a global selector model optimizing fidelity of interpretations.
result Predictions can be encoded within interpretations, detected by EVAL-X.
Combines global and local features for better social circle prediction in ego-networks.
problem Efficiently analyzing ego-networks with hidden local structures.
method Evolved deep learning techniques to capture both global and local network features.
result Social circle prediction benefits from a combination of global and local features.
A new method detects financial fraud using graph transformers.
problem Detecting fraudulent transactions in financial data.
method Spatial-Temporal-Aware Graph Transformer (STA-GT) integrating GNNs and transformers.
result STA-GT outperforms general GNN models on financial fraud detection.
A new method tackles Bayesian inverse problems with complex PDEs.
problem Bayesian inverse problems with expensive forward model evaluations and high-dimensional priors.
method Domain-decomposed variational auto-encoder Markov chain Monte Carlo (DD-VAE-MCMC) method.
result The method efficiently solves Bayesian inverse problems in parallel and low-dimensional latent spaces.
We propose a novel node embedding of directed graphs to statistical manifolds, which is based on a global minimization of pairwise relative entropy and graph geodesics in a non-linear way. Each node is encoded with a probability density function over a measurable space. Furthermore, we analyze the connection between th…
We provide a method to prepare covariance matrices for quantum datasets.
problem No concrete protocol for preparing covariance matrices for quantum datasets.
method Amplitude encoding of data, exploiting global phase symmetry to center the dataset.
result Covariance matrix can be prepared for arbitrary quantum datasets or centered classical datasets.
TMTF improves time series visualization by separating dynamic regimes.
problem Misleading global transition matrix in time series analysis.
method Temporal chunking, local transition matrices, and image assembly.
result Temporal segmentation reveals distinct transition dynamics.
Paper studies Transformer learning theory for Euclidean and Riemannian domains.
problem Understanding and optimizing Transformer networks for regression tasks.
method Constructive approximation framework using softmax partition of unity and attention mechanism.
result Transformer can achieve uniform ε-approximation error with minimal parameters.
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 new method for feature fusion in U-Net decoders using difference-based gating.
problem Precise fusion of high-level semantics and low-level details in U-Net decoder reconstruction.
method Proposes two difference-based gating approaches: Feature-difference gating (FDG) and Entropy-difference gating (EDG).
result Both FDG and EDG methods outperform existing attention-based fusion methods, with EDG showing superior performance.
Develops a flexible deep autoencoding topic model with scalable hybrid Bayesian inference.
problem Flexible and interpretable document analysis models.
method DATM with hybrid Bayesian inference, including topic-layer-adaptive stochastic gradient Riemannian MCMC and Weibull variational encoder.
result Demonstrates scalability and efficacy on big corpora in unsupervised and supervised learning tasks.
Global well-posedness and asymptotic convergence for vacuum Einstein's equations proved.
problem Proving global well-posedness and asymptotic convergence for vacuum Einstein's equations.
method Integrable damping mechanism induced by cosmological constant.
result Future-global solutions converge smoothly to a limiting metric of constant negative scalar curvature.
Let M be an oriented compact 3-manifold and let T be a (loose) triangulation of M, with ideal vertices at the components of the boundary of M and possibly internal vertices. We show that any spin structure s on M can be encoded by extra combinatorial structures on T. We then analyze how to change these extra structures…
EAGLE-Net enhances foundation models by integrating patch-level features for better tissue understanding.
problem Foundation models lack mechanisms for global tissue structure and local context in computational pathology.
method EAGLE-Net combines multi-scale spatial encoding, attention-guided loss functions, and background suppression to aggregate patch-level features into slide-level predictions.
result EAGLE-Net improves classification accuracy and concordance indices across multiple cancer types, producing biologically coherent attention maps.
HGConv uses HRR to efficiently detect malware, outperforming existing methods.
problem Efficiently detecting malware with long sequences.
method Holographic Global Convolutional Networks (HGConv) utilizing Holographic Reduced Representations (HRR).
result Achieved state-of-the-art results on malware benchmarks.
SyncRank recovers global ranking from noisy comparisons with theoretical guarantees.
problem Recovering a global ranking from noisy pairwise comparisons.
method Complex-valued data model and SDP relaxation for exact ranking recovery.
result SyncRank achieves exact ranking recovery with high probability above a critical noise threshold of O(sqrt(n / log n)).
Missing data imputation (MDI) is a fundamental problem in many scientific disciplines. Popular methods for MDI use global statistics computed from the entire data set (e.g., the feature-wise medians), or build predictive models operating independently on every instance. In this paper we propose a more general framework…
Neural Physicist learns physical dynamics from images.
problem Learning meaningful physical state representations and accurate state transitions from image sequences.
method Neural Physicist uses VAE for state extraction, NP for parameters, and SSM for dynamics.
result Achieves long-term predictions and identifies system degrees of freedom.
We develop a ``canonical Wick rotation-rescaling theory in 3-dimensional gravity''. This includes: (a) A simultaneous classification that shows how generic maximal globally hyperbolic spacetimes of constant curvature, which admit a complete Cauchy surface (in particular a compact one), as well as complex projective str…
A central goal of meta-learning is to find a learning rule that enables fast adaptation across a set of tasks, by learning the appropriate inductive bias for that set. Most meta-learning algorithms try to find a \textit{global} learning rule that encodes this inductive bias. However, a global learning rule represented …
Hybrid QML model improves recovery rate prediction accuracy.
problem Complex nonlinear dependencies, high-dimensional feature spaces, and limited sample sizes in recovery rate forecasting.
method Hybrid Quantum Machine Learning (QML) with Amplitude Encoding, leveraging PQC and qubit data compression.
result Significantly lower RMSE (0.228) compared to classical models.
GNNRank uses neural networks to learn global rankings from competition match data.
problem Learning global rankings from pairwise comparisons in directed graphs.
method Proposes GNNRank, a trainable GNN-based framework with digraph embedding and new objectives.
result GNNRank achieves competitive and superior performance compared to baselines.
Novel flows generate molecules without post-processing.
problem Generating new molecules efficiently and without post-processing issues.
method Continuous normalizing E(3)-equivariant flows based on node ODEs coupled as a graph PDE.
result Generated samples achieve state-of-the-art performance on QM9 and ZINC250K benchmarks.