Regularization effect found in neural feature alignment.
problem Implicit regularization in deep learning models.
method Geometrical viewpoint and analysis of Rademacher complexity.
result Neural features align along task-relevant directions, leading to regularization.
Deep neural networks show some layers better align with data than others.
problem Understanding why some layers in deep neural networks better align with data.
method Introducing the Equilibrium Hypothesis to connect alignment pattern to signal propagation.
result The Equilibrium Hypothesis explains the ascent-descent pattern of alignment in deep neural networks.
A new method improves density ratio estimation with fewer function evaluations.
problem Stable and accurate estimation of density ratios with high variance issues.
method Diffusion Secant Alignment for Score-Based Density Ratio Estimation (ISA-DRE)
result ISA-DRE achieves comparable or superior results with fewer function evaluations.
NTKs explain GNNs' alignment for graph prediction.
problem Understanding GNNs' alignment for graph prediction.
method Analyzing NTKs and alignment in GNNs, focusing on cross-covariance.
result Optimizing alignment in GNNs optimizes graph representation.
Geometric framework for aligning fiber tracts across subjects.
problem Challenges in finding direct tract correspondence across multiple individuals.
method Geometric framework using intrinsic mean and deformation fields, parallel transport for registration.
result Bundle alignment results on 43 healthy adult subjects.
The study explains how neural networks align their kernels to target functions during training.
problem Understanding how neural networks align their kernels to target functions during training.
method Theoretical analysis of kernel evolution in toy models and deep networks.
result Kernel alignment naturally emerges during training to accelerate convergence and improve generalization.
Neural networks can learn kernel machines with a data-dependent kernel.
problem Can neural networks in the rich feature learning regime learn a kernel machine?
method Demonstrated silent alignment effect in neural networks, showing they can learn a kernel machine with a data-dependent kernel.
result Neural networks in the rich feature learning regime can learn a kernel machine with a data-dependent kernel due to silent alignment.
New learning rules for wide neural networks without backpropagation.
problem Training wide neural networks efficiently and without backpropagation.
method Input-weight alignment driven by gradient descent in the NTK regime.
result Biologically-motivated learning rules equivalent to backpropagation in wide networks.
NTK-SAP improves neural network pruning by aligning training dynamics.
problem Improving neural network pruning to reduce training time and memory.
method Prune connections based on the spectrum of the Neural Tangent Kernel (NTK), using multiple random weight realizations and random inputs.
result Empirically, NTK-SAP achieves better performance than all baselines on multiple datasets.
Proposes a new method for better explaining neural network decisions.
problem Challenges in explaining neural network decisions due to base-point choice.
method Introduces tangentially aligned integrated gradients to maximize explanation tangential alignment.
result Optimal base-point maximizes explanation tangential alignment, leading to more accurate interpretations.
Gradient descent aligns neural feature matrices with pre-activation tangent features.
problem Understanding neural feature learning mechanisms.
method Analytical proof of alignment between weight matrices and pre-activation tangent features.
result Derivative alignment occurs almost surely in high-dimensional settings.
The paper analyzes how deep models memorize spurious features.
problem Understanding how deep models memorize spurious features in training data.
method Characterizes spurious feature memorization via model stability and feature alignment.
result Memorization of spurious features weakens as generalization capability increases.
New method shortens and straightens curves, proving convergence and well-posedness.
problem Shortening and straightening of curves.
method Conceptual shift in curve shortening to tangent aligning, variational study of geometric flows.
result Proves convergence to a straight line and global well-posedness for various geometric flows.
Survey on finite dimensional Lie groups over real numbers.
problem Lack of rigorous proofs for Lie groups using tangent space formalism.
method Formalism of tangent space via chart and vector methods, curve and derivation methods.
result Rigorous proofs of Lie groups facts with this formalism.
The paper develops methods to reduce deployment risk under dynamic covariate shifts.
problem Reduction of deployment risk under dynamic covariate shifts.
method Time-domain Poincare inequality and Jacobian-velocity theorem to identify and control directional tangent energy.
result Drift-aligned tangent regularization (DTR) reduces risk volatility and directional gain in low-rank drift regimes.
TopoNTK kernel captures higher-order interactions in simplicial complexes.
problem Graph neural networks miss higher-order interactions in relational systems.
method Introduces TopoNTK, an infinite-width kernel for simplicial message passing.
result TopoNTK captures topology invisible to graph kernels, improving expressivity and interpretability.
The paper reveals low-rank structure in neural network gradients, influenced by data and model parameters.
problem Investigating low-rank structure in gradients of neural networks under relaxed assumptions.
method Spiked data model, relaxation of isotropy assumptions, analysis of mean-field and neural-tangent-kernel scalings.
result Gradient of input weights is approximately low rank, dominated by two rank-one terms.
LEGO estimates tangent spaces more robustly than LPCA in noisy data.
problem Estimating tangent spaces in high-noise settings.
method Spectral method using graph Laplacian eigenvectors and gradient orthogonization.
result LEGO yields more robust tangent space estimates than LPCA.
Paper solves robust multi-dimensional scaling with accelerated projections.
problem Localize point locations from noisy pairwise distances.
method Alternating projections with tangent space acceleration.
result Linear convergence of reconstructed points to original points.
This paper addresses anisotropy in Transformer models, providing geometric insights and empirical support.
problem Anisotropy phenomenon in Transformer models, challenging their geometric interpretation.
method Derive geometric arguments and use concept-based mechanistic interpretability during training.
result Activation-derived directions capture large gradient energy and a larger share of gradient anisotropy than normal controls.
Geometric framework analyzes bias in variational inference for posterior functionals.
problem Analyzing the bias of posterior functionals under variational approximations.
method Developed a geometric framework to evaluate the bias of posterior functionals using the variational tangent space.
result The leading-order bias of a posterior functional is determined by its component orthogonal to the variational tangent space.
Confocal conics form an orthogonal net. Supplementing this net with one of the following: 1) the net of Cartesian coordinate lines aligned along the principal axes of conics, 2) the net of Apollonian pencils of circles whose foci coincide with the foci of conics, 3) the net of tangents to a conic of the confocal family…
A set of equations is developed to describe a curve in space given the curvature κ and the angle of rotation θ of the osculating plane. The set of equations has a solution (in terms of κ and θ) that indirectly solves the Frenet-Serret equations, with a unique value of θ for each specified value of τ. Explic…
Expressiveness and generalization of deep models was recently addressed via the connection between neural networks (NNs) and kernel learning, where first-order dynamics of NN during a gradient-descent (GD) optimization were related to gradient similarity kernel, also known as Neural Tangent Kernel (NTK). In the majorit…
Neighborhood sampling affects graph neural network training outcomes.
problem Understanding the impact of neighborhood sampling on graph neural network training.
method Theoretical analysis using neural tangent kernels and Gaussian processes.
result Posterior covariance differs for different neighborhood sampling approaches, indicating no dominant approach.
The paper explains spikes in training loss as catapults, improving feature learning and generalization.
problem Understanding and improving the training process of neural networks.
method Analysis of training loss spikes in SGD, empirical evidence of catapults, and demonstration of AGOP alignment.
result Catapults in training loss promote feature learning and better generalization.
We analyze the performance of a class of manifold-learning algorithms that find their output by minimizing a quadratic form under some normalization constraints. This class consists of Locally Linear Embedding (LLE), Laplacian Eigenmap, Local Tangent Space Alignment (LTSA), Hessian Eigenmaps (HLLE), and Diffusion maps.…
New method uses contours of segmented images for X-ray classification.
problem Classifying X-ray images of segmented radiography.
method Develops a new approach for image analysis of multivariate planar curves, addressing alignment issues.
result Demonstrates the robustness and appeal of the proposed method through detection of cardiomegaly and numerical experiments.
Deep networks converge in direction, with implications for predictions and margins.
problem Understanding convergence and alignment in deep learning networks.
method Developed a theory of unbounded nonsmooth Kurdyka-Łojasiewicz inequalities for functions definable in an o-minimal structure.
result Network weights, predictions, training errors, and margin distribution converge in direction and align with gradient flow.
This paper studies nonlinear representation learning dynamics beyond the NTK regime.
problem Efficient reasoning and inference in raw sensory data representations.
method Identifies common model structure assumption and data-architecture alignment condition for global convergence and optimality.
result Theoretical framework explains network size effects and provides practical model structure guidelines.
This paper surveys scalable automated alignment methods for LLMs.
problem Scalability issues in traditional human-annotated alignment methods for LLMs.
method Categorizes and discusses various automated alignment methods.
result Emerging automated alignment methods are effective and scalable.
Inference-aware meta-alignment of LLMs reduces computational cost.
problem Aligning LLMs to diverse human preferences is challenging due to conflicting criteria.
method IAMA trains a base model to be aligned to multiple tasks via different inference-time alignment algorithms, using non-linear GRPO for optimization.
result IAMA enables effective alignment of LLMs to multiple criteria with limited computational budget.
Conformal Alignment ensures trustworthy outputs from foundation models.
problem Ensuring outputs from foundation models align with human values in high-stakes tasks.
method A framework that trains an alignment predictor using reference data to select trustworthy outputs.
result Conformal Alignment accurately identifies trustworthy outputs via lightweight training over moderate reference data.
Analysis of deep neural networks under various learning rules reveals dynamics of feature and prediction learning.
problem Understanding how different learning rules affect feature and prediction dynamics in deep neural networks.
method Analysis of infinite-width deep networks trained with gradient descent and various learning rules.
result The evolution of the output function is governed by an effective neural tangent kernel (eNTK), which varies depending on the learning rule and training regime.
This paper introduces tangent display maps to simplify tangent category theory.
problem The category of smooth manifolds does not admit all pullbacks, complicating tangent category theory.
method Develops tangent display maps as a special class of maps well-behaved with respect to pullbacks.
result Tangent display maps simplify previous work in tangent categories and provide a new way to define open subobjects.
Paper constructs infinitely many tangent functors on diffeological spaces.
problem Tangent spaces in diffeological spaces are not uniquely defined.
method Introduced and constructed infinitely many non-isomorphic tangent functors.
result The choice of tangent functor is not unique outside smooth manifolds.
LPL optimizes embeddings to align local neighborhoods, improving cross-lingual word alignment.
problem Aligning embeddings across different datasets and languages.
method Locality Preserving Loss (LPL) optimizes model to project embeddings while maintaining local neighborhoods and aligning them.
result LPL-based alignment leads to better and consistent accuracy, especially in small training set settings.
Extends reinforcement learning alignment to scalar rewards, improving math reasoning.
problem Designing reinforcement learning algorithms for general LLM alignment.
method Introduces f-GRPO and f-HAL, estimating f-divergences between reward-aligned and unaligned distributions.
result Improves math reasoning RLVR tasks and mitigates reward hacking.
The paper proposes a learning-theoretic perspective on representation alignment.
problem Understanding how AI models' representations become aligned as they scale.
method Reviewing and connecting different notions of alignment, focusing on stitching.
result Relating properties of stitching to kernel alignment of representations.
Survey of alignment techniques for large language models.
problem Ensuring large language models align with human values.
method Analysis of diverse alignment methods and training paradigms.
result Preference-based methods offer more flexibility for nuanced alignment.
The paper addresses rigid alignment of noisy patches, providing a polynomial time algorithm and convergence conditions.
problem Finding a rigid alignment of overlapping local views (patches) that minimizes alignment error in a noisy setting.
method Characterizes non-degeneracy based on kernel and positivity of a matrix, provides polynomial time algorithm for testing non-degeneracy, and uses Riemannian gradient descent for alignment.
result The algorithm converges locally linearly to a non-degenerate perfect alignment under certain conditions.
PolyILR: A Tree-Structured Orthonormal Decomposition of Compositional Data
problem Representing compositional data with hierarchical structure
method PolyILR: A canonical orthonormal decomposition of the Aitchison tangent space aligned with any tree topology
result PolyILR yields stable, interpretable features and enables inference at multiscale tree resolution
Study connects database alignment and planted matching using Gaussian features.
problem Identify matching between correlated user features in anonymized databases.
method Derived results for database alignment and planted matching, showing connections and thresholds.
result Performance thresholds for database alignment converge to planted matching when feature dimensionality is sufficiently high.
Study on triviality of tangent and generalized tangent bundles of manifolds.
problem Triviality of tangent and generalized tangent bundles of manifolds.
method Analyzing relations between tangent bundle TM and generalized tangent bundle TM=TM⊕T∗M of manifolds. result The generalized tangent bundle of a parallelizable manifold is trivial, but the converse is not always true.
Bayesian framework proves thresholds for multi-graph alignment feasibility.
problem Determining when multi-graph alignment is statistically possible.
method Developed a Bayesian estimation framework over metric spaces.
result Identified thresholds for Gaussian and sparse Erdős-Rényi models.
SMAI framework tests and integrates single-cell data alignability.
problem Lack of a rigorous statistical test for alignability and distortion during alignment.
method Spectral manifold alignment and inference (SMAI) framework.
result SMAI outperforms existing methods in alignability testing and integration.
New method aligns brain data across individuals for better brain decoding.
problem Inter-individual variability in brain response patterns limits decoder generalization.
method SpectralOT method that embeds cortical geometry into Laplace-Beltrami eigenmodes.
result SpectralOT strikes balance between aligning functional features and preserving anatomical structure.
Method aligns multilingual news for better stock return prediction.
problem Losing nuances in multilingual news translations.
method Optimal transport for sentence alignment.
result Aligned sentences correlate better with stock returns.