UNTIE learns representations of coupled categorical data.
problem Challenges in learning from unlabeled categorical data with complex couplings.
method UNTIE approach for unsupervised representation learning of heterogeneous couplings.
result UNTIE significantly improves categorical data representations on 25 diverse datasets.
C2VAE learns disentangled and coupled representations without prior knowledge.
problem Learning disentangled and coupled representations in latent space.
method Introduces C2VAE, a self-supervised VAE that factorizes posterior and uses Gaussian copula for dependencies. result Demonstrates strong effect in enhancing disentangled representation learning.
DS2CF-Net learns hierarchical representations with deep coupled factorization and enriched prior.
problem Learning deep hierarchical representations from data.
method Dual-constrained Deep Semi-Supervised Coupled Factorization Network (DS2CF-Net) with enriched prior.
result DS2CF-Net achieves state-of-the-art performance in representation learning and clustering.
A general form for the boundary coupling of a Lie algebroid Poisson sigma model is proposed. The approach involves using the Batalin-Vilkovisky formalism in the AKSZ geometrical version, to write a BRST-invariant coupling for a representation up to homotopy of the target Lie algebroid or its subalgebroids. These consid…
Research decouples Lie algebroids using bicocycle double cross product theory.
problem Understanding decoupling and coupling phenomena in Lie algebroids.
method Bicocycle double cross product realization method.
result Unified product, double cross product, semi-direct product, and cocycle extension frameworks are instances of the general method.
Deep model learns coupled representations from side information for sparse signal recovery.
problem Recovering signals from undersampled, incomplete or noisy linear measurements.
method Deep unfolding model incorporating side information from different modalities.
result Superior performance compared to single-modal and multimodal methods.
We develop a stochastic target representation for Ricci flow and normalized Ricci flow on smooth, compact surfaces, analogous to Soner and Touzi's representation of mean curvature flow. We prove a verification/uniqueness theorem, and then consider geometric consequences of this stochastic representation. Based on this …
Representation learning is an essential problem in a wide range of applications and it is important for performing downstream tasks successfully. In this paper, we propose a new model that learns coupled representations of domains, intents, and slots by taking advantage of their hierarchical dependency in a Spoken Lang…
Unified analytic account of correlation emergence and Epps effect in coupled limit order books
problem Correlation emergence and Epps effect in coupled limit order books
method Discrete random-walk description of order flow with creation, cancellation, and diffusion, coupled reaction-diffusion equations with moving reaction boundary
result Realized correlations as a function of aggregation time
CF-INNs can approximate any invertible function, resolving a long-standing problem.
problem Whether CF-INNs can approximate any invertible function.
method Demonstrated CF-INNs are universal approximators for invertible functions by showing a convenient criterion.
result CF-INNs are universal approximators for invertible functions.
C-VAE improves VAE by resolving prior issues and generating better samples.
problem Low-quality samples from VAE due to prior issues.
method Formulates VAE as OT, allows flexible priors, and uses OT formulations.
result C-VAE generates higher quality samples and latent representations.
A new ZSL algorithm uses shared sparse representations for unseen classes.
problem Classifying images from unseen classes using only semantic information.
method Coupled dictionary learning to represent visual and semantic features in an intermediate space.
result The proposed method outperforms state-of-the-art ZSL algorithms on benchmark datasets.
Nonparametric Bayesian approaches to clustering, information retrieval, language modeling and object recognition have recently shown great promise as a new paradigm for unsupervised data analysis. Most contributions have focused on the Dirichlet process mixture models or extensions thereof for which efficient Gibbs sam…
In the artificial intelligence field, learning often corresponds to changing the parameters of a parameterized function. A learning rule is an algorithm or mathematical expression that specifies precisely how the parameters should be changed. When creating an artificial intelligence system, we must make two decisions: …
Derives a formula for fermion dimensions in spherically symmetric monopole backgrounds.
problem Calculating the dimension of the plane-wave normalizable kernel for massless fermions in spherically symmetric monopole backgrounds.
method Derives a formula for the dimension of the plane-wave normalizable kernel of the Dirac operator for fermions of any representation of SU(N) in the presence of any spherically symmetric monopole background.
result Derives a formula for the dimension of the plane-wave normalizable kernel of the Dirac operator.
Chaos in cerebellar cells enhances complexity of neural patterns.
problem Understanding how cerebellar granular layer represents complex information.
method Constructed a model of cerebellar granular layer with gap junctions, evaluated using reservoir computing.
result Chaotic dynamics in the cerebellar granular layer produce complex and diverse output patterns.
TIME network simplifies complex physical processes with interpretable models.
problem Challenges in learning coupled dynamic processes from multiple observations.
method Fully convolutional architecture capturing invariant domain structure.
result Robust and transparent in capturing process kernels and anomalies.
A new method for conditional sampling using paired Wasserstein Autoencoders.
problem Conditional sampling from complex data distributions.
method Derive a novel loss function for Wasserstein Autoencoders to enable sampling from OT-type couplings.
result Learned cost-optimal transport maps and conditional sampling from an OT-type coupling.
This paper shows how learning the phase-amplitude coupling improves bio-signal classification.
problem Discarding phase component in bio-signal feature extraction leads to poor generalization.
method Introducing a novel self-supervised learning task called Phase-Swap to detect phase-amplitude coupling.
result Neural networks trained on Phase-Swap task generalize better across subjects and recording sessions.
A new framework optimizes fMRI and behavioral data for better understanding of Autism.
problem Linking complex fMRI data to behavioral measures is challenging.
method Coupled manifold optimization framework projecting fMRI onto a shared manifold and mapping to behavioral measures.
result Framework outperforms traditional methods in predicting clinical severity of Autism.
This paper shows how to approximate any log-concave distribution using well-conditioned affine coupling flows.
problem Understanding the representational power of affine coupling flows for log-concave distributions.
method Leveraging connections between affine coupling architectures, Langevin dynamics, and Hénon maps to prove log-concave approximation.
result Any log-concave distribution can be approximated using well-conditioned affine-coupling flows.
A method uses autoencoders to align multi-modal neuron data.
problem Inconsistent cell type definitions across different data modalities.
method Coupled training of autoencoders for cross-modal alignment.
result Representations learned by coupled autoencoders can identify single-modality sampled cell types.
We investigate in this paper the architecture of deep convolutional networks. Building on existing state of the art models, we propose a reconfiguration of the model parameters into several parallel branches at the global network level, with each branch being a standalone CNN. We show that this arrangement is an effici…
CFIL uses coupled flows to model state distributions for imitation learning.
problem Lack of explicit modeling of state distributions in reinforcement and imitation learning.
method Coupled normalizing flows for state and state-action distributions.
result CFIL achieves state-of-the-art performance on benchmark tasks.
We study cascades on a two-layer multiplex network, with asymmetric feedback that depends on the coupling strength between the layers. Based on an analytical branching process approximation, we calculate the systemic risk measured by the final fraction of failed nodes on a reference layer. The results are compared with…
We address representational challenges in normalizing flows, particularly depth and conditioning issues.
problem Challenges in training normalizing flows, including vanishing/exploding gradients and poor conditioning.
method Analyzes representational aspects of depth and conditioning in normalizing flows, proving theoretical bounds and investigating phenomena.
result Proves that shallow affine coupling networks are universal approximators in Wasserstein distance if ill-conditioning is allowed.
Representation learning is typically applied to only one mode of a data matrix, either its rows or columns. Yet in many applications, there is an underlying geometry to both the rows and the columns. We propose utilizing this coupled structure to perform co-manifold learning: uncovering the underlying geometry of both …
New model learns multimodal data better than DAGs.
problem Complex multimodal data not well captured by DAGs.
method Latent partial causal model with two latent coupled variables.
result Identifiability result shows representations correspond to latent variables.
Scattering representations simplify SBI for images without extra compression.
problem Efficiently performing simulation-based inference on images with limited data.
method Use scattering representations for compression and learning, combined with spatial averaging and expressive density estimators.
result Scattering representations provide more information than traditional methods, without requiring additional simulations.
New volume invariant for cocycles of hyperbolic lattices, proving rigidity results.
problem Volume calculation for cocycles of hyperbolic lattices.
method Introducing a new volume invariant and proving Milnor-Wood type inequalities.
result Characterization of maximal cocycles and proof of rigidity results.
Physics-constrained deep learning predicts geophysical dynamics with boundedness.
problem Forecasting geophysical systems with hidden variables and incomplete observations.
method Physics-constrained neural ordinary differential equation (NODE) representations with boundedness constraints.
result The approach generalizes learned dynamics to arbitrary initial conditions.
A new method combines OCSVM with representation learning for UAD.
problem Detect anomalies without labeled data, especially in rare or unavailable cases.
method Custom loss formulation that aligns latent features with OCSVM decision boundary.
result Succeeds in detecting small, non-hyperintense lesions in MRI.
New method uncovers zero entropy in dependent observations after finite samples.
problem Understanding uncertainty reduction in dependent observations.
method Minimum list entropy coupling, greedy algorithm.
result Zero entropy achieved with O(log(1/P_min)) samples for dependent observations.
We consider dimensional reduction of gauge theories with arbitrary gauge group in a formalism based on equivariant principal bundles. For the classical gauge groups we clarify the relations between equivariant principal bundles and quiver bundles, and show that the reduced quiver gauge theories are all generically buil…
New theory predicts deep neural networks can operate in an extended critical regime without fine-tuning.
problem Understanding the dynamics and computational principles of deep neural networks.
method Combining theories of heavy-tailed random matrices and non-equilibrium statistical physics.
result Deep neural networks can operate in an extended critical regime without fine-tuning parameters.
Training-free source selection for LLM families with shared vocabularies
problem Source selection for LLM families with shared vocabularies
method Fisher alignment at vocabulary scale
result Fisher alignment is a cosine between kernel mean embeddings in the joint activation-error space
This work shows how disentangled and sparse representations improve multi-task learning.
problem Improving generalization in multi-task learning with disentangled and sparse representations.
method Proved a new identifiability result and proposed a practical approach using sparsity-promoting bi-level optimization.
result Maximally sparse base-predictors yield disentangled representations under certain conditions.
A popular approach for predicting the future of dynamical systems involves mapping them into a lower-dimensional "latent space" where prediction is easier. We show that the information-theoretically optimal approach uses different mappings for present and future, in contrast to state-of-the-art machine-learning approac…
Multi-domain translation seeks to learn a probabilistic coupling between marginal distributions that reflects the correspondence between different domains. We assume that data from different domains are generated from a shared latent representation based on a structural equation model. Under this assumption, we show th…
ExpBERT uses natural language explanations to improve text interpretation.
problem Improving text interpretation for relation extraction tasks.
method Fine-tuning BERT on MultiNLI to interpret natural language explanations.
result ExpBERT matches a BERT baseline but requires less labeled data and improves performance.
Improved flow-based models capture dependencies better with multi-scale autoregressive priors.
problem Limited expressiveness of flow-based models for long-range data dependencies.
method Introducing channel-wise dependencies through multi-scale autoregressive priors (mAR) in split coupling flow layers (mAR-SCF).
result Achieves state-of-the-art density estimation results on MNIST, CIFAR-10, and ImageNet.
Deep learning has recently been shown to be instrumental in the problem of domain adaptation, where the goal is to learn a model on a target domain using a similar --but not identical-- source domain. The rationale for coupling both techniques is the possibility of extracting common concepts across domains. Considering…
The Bogomol'nyi-Prasad-Sommerfield (BPS) multi-wall solutions are constructed in supersymmetric U(N_C) gauge theories in five dimensions with N_F(>N_C) hypermultiplets in the fundamental representation. Exact solutions are obtained with full generic moduli for infinite gauge coupling and with partial moduli for finite …
Motivated by the study of coupled Kähler-Einstein metrics by Hultgren and Witt Nyström and coupled Kähler-Ricci solitons by Hultgren, we study in this paper coupled Sasaki-Einstein metrics and coupled Sasaki-Ricci solitons. We first show an isomorphism between the Lie algebra of all transverse holomorphic vector fields…
Derives a family of hyperparameter scaling strategies for neural networks.
problem Optimizing hyperparameters for wide and deep neural networks.
method Introduces a one-parameter family of hyperparameter scaling strategies.
result Reveals proper scaling of depth with width for large-scale models.
Novel framework detects CKD in diabetic patients using sparse EHR representations.
problem Early detection of CKD in diabetic patients.
method Sparse longitudinal representations of EHR data.
result Proposed model achieves higher predictive performance than baselines.
Defines coupled embeddability for maps on products of spaces, generating examples and nonexamples.
problem Understanding when maps on products of spaces can be embedded.
method Uses known results for nonsingular biskew and bilinear maps, studies genericity properties, extends Whitney embedding theorems, and relates to Z/2-coindex of embedding spaces. result Generates strong obstructions to coupled embeddability in terms of combinatorics of triangulations.
Free lunch from noise reveals linear spectral features for RL.
problem Trade-off between expressiveness and tractability in RL.
method Noise assumption and Spectral Dynamics Embedding (SPEDE).
result SPEDE breaks the trade-off and completes optimistic exploration.