Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

36912 · Oct 202419922001200920172026
48 results for Monge SAM

Monge SAM improves deep learning by making sharpness-aware minimization invariant to reparametrizations.

problem Non-invariance of sharpness-aware minimization (SAM) to reparametrizations.
method Introduces Monge SAM, a reparametrization-invariant version of SAM using a Riemannian metric.
result Monge SAM enhances robustness and generalization compared to previous methods.

This work analyzes statistical properties of SAM, showing it outperforms GD.

problem Improving deep neural network generalization through flatter solutions.
method Directly studies statistical performance of Sharpness-Aware Minimization (SAM).
result SAM has smaller prediction error than Gradient Descent (GD) under certain conditions.

SAM selects flatter minima late in training, improving generalization.

problem Improving neural network generalization under various settings.
method Sharpness-Aware Minimization (SAM) applied late in training.
result SAM efficiently selects flatter minima late in training, improving generalization.

SAM improves deep learning tasks by promoting balancedness, reducing outlier impact.

problem Improving generalization in deep learning tasks, especially with scale-invariant problems.
method Introduces balancedness as a new concept to depict global behaviors of SAM, focusing on the difference between squared norms of two variables.
result SAM promotes balancedness and is data-responsive, outperforming SGD in outlier scenarios.

SAM optimizer struggles to converge to global minima or stationary points in practical settings.

problem Limited convergence of SAM optimizer to global minima or stationary points in practical scenarios.
method Deterministic and stochastic versions of SAM with constant perturbation size and gradient normalization were studied.
result SAM has limited capability to converge to global minima or stationary points in many scenarios.

Overparameterization enhances SAM's effectiveness in minimizing sharpness.

problem Improving generalization in deep neural networks.
method Analysis of Sharpness-Aware Minimization (SAM) under varying degrees of overparameterization.
result Overparameterization significantly improves SAM's performance, particularly in noisy and sparse settings.

SAM improves neural network generalization by penalizing sharpness, clarifying its exact notion and mechanism.

problem Improving deep neural network generalization for various settings.
method Sharpness-Aware Minimization (SAM) technique that penalizes a notion of sharpness of the model.
result SAM regularizes the third notion of sharpness, most likely preferred for practical performance.

LSAM optimizes deep learning training with improved efficiency.

problem Inefficiency in distributed large-batch training with Sharpness-Aware Minimization (SAM).
method Integrates SAM's adversarial steps with an asynchronous distributed sampling strategy.
result Higher final accuracy compared to data-parallel SAM.

This work connects SAM to variational inference and evaluates its performance.

problem Improving generalization of gradient-based learning by finding flat minima.
method Establishes connections between SAM and Mean-Field Variational Inference (MFVI), and evaluates variational algorithms combining or interpolating between SAM and MFVI.
result SAM-like updates can be used as a drop-in replacement for the reparametrisation trick.

This paper improves SAM by reformulating it as a bilevel optimization problem.

problem Improving Sharpness-Aware Minimization (SAM) for better performance.
method Reformulate SAM as a bilevel optimization problem using a 0-1 loss surrogate.
result BiSAM consistently results in improved performance compared to SAM and its variants.

SAM optimizer benefits from normalization, stabilizing and guiding optimization.

problem Improving deep neural network performance with SAM optimizer.
method Theoretical and empirical study of normalization in SAM for convex and non-convex functions.
result Normalization helps SAM in stabilizing and guiding optimization along a continuum of minima.

SAM improves generalization in overparameterized models, but its behavior in tensorized models is less understood.

problem Understanding the implicit regularization of SAM in tensorized models.
method Scale-invariance analysis and gradient flow analysis to derive Norm Deviation as a measure of core norm imbalance, and propose Deviation-Aware Scaling (DAS).
result DAS achieves competitive or improved performance over SAM, while offering reduced computational overhead.

New method μP2μP^2 improves neural network training by scaling perturbations layerwise.

problem Improving neural network performance as models scale up.
method Layerwise perturbation scaling in the infinite-width limit of neural networks.
result Layerwise perturbation scaling ensures all layers are effectively perturbed in the limit.

LEARN-SAM improves RL from sub-optimal demonstrations by localizing expert policies and selectively using demonstrations.

problem Improving RL from sub-optimal or sparse demonstrations.
method Local Ensemble and Reparameterization with Split and Merge of expert policies (LEARN-SAM).
result LEARN-SAM boosts learning speed and accuracy by selectively using demonstrations.

New adaptive scheduler improves SAM for better model training.

problem Training machine learning models requires selecting a learning rate, which is often difficult and time-consuming.
method Derive Polyak schedulers tailored to SAM-style updates, proving linear convergence for strongly convex objectives and an O(1/T) rate for convex objectives.
result Polyak schedulers achieve comparable or better performance than tuned SAM baselines, reducing the need for learning-rate tuning.

SAMS-VAE models cellular perturbations using sparse additive mechanisms.

problem Modeling effects of diverse interventions on cells.
method Sparse Additive Mechanism Shift Variational Autoencoder (SAMS-VAE).
result SAMS-VAE identifies disentangled, perturbation-specific latent subspaces.

Develops new methods to evaluate data influence in SAM for improved model training.

problem Challenges in mislabeled noisy data and privacy concerns in SAM.
method Two innovative data valuation methods based on influence functions (IF) for SAM.
result Demonstrates effectiveness in identifying mislabeled data and enhancing interpretability.

LORENZA improves LLM fine-tuning efficiency and generalization.

problem Improving robustness and generalization of LLMs under hardware constraints.
method AdaZo-SAM and LORENZA, combining Adam and SAM with zeroth-order estimation and randomized SVD.
result LORENZA achieves better generalization and reduced memory consumption compared to existing methods.

New optimization method improves generalization across various tasks.

problem Improving zeroth-order optimization for better generalization.
method Exponential tilting objective to connect zeroth-order optimization with sharpness-aware minimization.
result Achieves better generalization compared to vanilla zeroth-order baselines.

SAM optimizes deep networks by oscillating between sides of the minimum.

problem Improving performance of deep networks.
method Gradient-based optimization method that oscillates between sides of the minimum.
result SAM effectively performs gradient descent on the spectral norm of the Hessian, encouraging drift towards wider minima.

A new causal discovery method, Structural Agnostic Modeling (SAM), is presented in this paper. Leveraging both conditional independencies and distributional asymmetries, SAM aims to find the underlying causal structure from observational data. The approach is based on a game between different players estimating each va…

2018-03-13abs ↗pdf ↗

A new spectrum attention mechanism improves time series classification.

problem Improving robustness and classification accuracy in time series classification.
method Proposes a spectrum attention mechanism (SAM) to filter and highlight important frequency components, using L1 regularization and a tumbling window for segmentation.
result Experimental results show that the proposed SSAM method produces better feature representations and improves classification accuracy.

DGSAM improves domain generalization by minimizing individual sharpness.

problem Improving domain generalization models that perform well on unseen target domains.
method Shifts DG paradigm toward minimizing individual sharpness across source domains.
result DGSAM reduces performance variance across domains with less computational overhead.

Agent-based model uses SAM to create realistic economic system.

problem Lack of tools to understand and predict economic crises.
method Agent-based modeling (ABM) with Social Accounting Matrix (SAM) calibration.
result ABM can produce economic systems close to real-world data.

SAM minimizes loss sharpness, improving adversarial transferability.

problem Improving adversarial transferability of deep neural networks.
method Evaluating surrogate models trained with seven minimizers, focusing on loss sharpness and flat neighborhoods.
result SAM minimizes loss sharpness, leading to better adversarial transferability.

We show that the classification performance of graph convolutional networks (GCNs) is related to the alignment between features, graph, and ground truth, which we quantify using a subspace alignment measure (SAM) corresponding to the Frobenius norm of the matrix of pairwise chordal distances between three subspaces ass…

2019-05-30abs ↗pdf ↗

New findings cast doubt on the role of λmaxλ_{max} in generalizing neural networks.

problem The role of λmaxλ_{max} in neural network generalization remains unclear.
method Experiments with various training interventions and batch sizes.
result Generalization benefits can vanish at larger batch sizes, challenging the role of λmaxλ_{max}.

Heretofore, neural networks with external memory are restricted to single memory with lossy representations of memory interactions. A rich representation of relationships between memory pieces urges a high-order and segregated relational memory. In this paper, we propose to separate the storage of individual experience…

2020-02-10abs ↗pdf ↗

New geometries derived from symplectic Monge-Ampère structures.

problem Exploring new generalized geometries from symplectic Monge-Ampère structures.
method Inspired by Hu, Moraru, and Svoboda, constructing new geometries from non-degenerate 2D symplectic Monge-Ampère structures.
result Non-degenerate Monge-Ampère structures give rise to quadric surfaces of generalized almost geometries.

The paper generalizes Monge-Ampère equations and their solutions in differential geometry.

problem Understanding the structure of Monge-Ampère equations and their solutions.
method Generalizing Monge-Ampère equations to higher-order systems and proving their solutions correspond to integral manifolds of exterior differential systems.
result The Korteweg-de Vries (KdV) equation and Cauchy-Riemann equations are examples of generalized Monge-Ampère equations.

Monge matrices and their permuted versions known as pre-Monge matrices naturally appear in many domains across science and engineering. While the rich structural properties of such matrices have long been leveraged for algorithmic purposes, little is known about their impact on statistical estimation. In this work, we …

2019-04-05abs ↗pdf ↗

Unique solution found for quaternionic Monge-Ampère equation on specific HKT manifolds.

problem Solving the quaternionic Monge-Ampère equation on HKT manifolds with an HKT foliation.
method Study of quaternionic Monge-Ampère equation on HKT manifolds with specific foliation properties.
result Unique solution for the equation for every basic datum.

Study proves long-term solutions to a specific equation on hyperKähler manifolds.

problem Proving long-term existence and uniqueness of solutions to a parabolic quaternionic Monge-Ampère equation.
method Proved long-term existence and uniqueness using parabolic quaternionic Monge-Ampère type equation.
result Solution converges smoothly to the unique solution of the Monge-Ampère equation.

Gradient and Laplacian estimates for complex Monge-Ampère equations found.

problem Estimating solutions to complex Monge-Ampère equations with singularities.
method Integral method applied to obtain gradient and Laplacian estimates.
result Gradient and Laplacian estimates for the solution to the singular complex Monge-Ampère equation.

Solves a Monge-Ampère type equation for Nakano positive curvature tensors of holomorphic vector bundles.

problem Solving Monge-Ampère type equations for Nakano positive curvature tensors of holomorphic vector bundles.
method Solves the Monge-Ampère type equation in the conformal class of a Nakano positive Hermitian metric.
result Solves the Monge-Ampère type equation for Nakano positive curvature tensors of holomorphic vector bundles.