ML PCA detects phase transitions in muon spectroscopy data.
problem Detecting phase transitions in materials using muon spectroscopy data.
method Unsupervised Machine Learning (PCA) applied to asymmetry functions.
result PCA method effectively detects phase transitions in muon spectroscopy experiments.
PCA improves detection of phase transitions in muon spectroscopy data from various materials.
problem Subtle changes in asymmetry function indicate phase transitions, but existing methods require material-specific knowledge.
method Applied unsupervised PCA to muon spectroscopy asymmetry data from multiple materials.
result PCA can recover phase transition indicators and improve detection of material-specific variations.
Muon optimizer outperforms GD in neural networks.
problem Optimizing matrix-structured parameters in neural networks.
method Muon optimizer specifically designed for matrix parameters, analyzing convergence rate and low-rank Hessian structure.
result Muon can outperform Gradient Descent due to its ability to leverage the low-rank structure of Hessian matrices.
Muon fails to converge on convex Lipschitz functions.
problem Understanding the convergence of Muon on convex and Lipschitz functions.
method Analyzing Muon's performance on convex and Lipschitz functions without error feedback.
result Muon does not converge on convex and Lipschitz functions, regardless of learning rate schedule.
Muon optimizer simplifies matrix optimization with spectral orthogonalization.
problem Matrix optimization challenges, especially with large condition numbers.
method Simplified Muon optimizer using spectral orthogonalization of gradients.
result Simplified Muon converges linearly with independent scalar sequences, outperforming gradient descent and Adam.
Muon outperforms GD in associative memory learning by balancing frequency components.
problem Training dynamics and scaling behavior of Muon in associative memory learning.
method Study of Muon in a linear associative memory model with softmax retrieval and hierarchical frequency spectrum over query-answer pairs.
result Muon achieves exponential speedup over GD in noiseless case and superior scaling efficiency in noisy case.
Muon optimizer improves deep learning with spectral norm constraints.
problem Improving optimization algorithms in deep learning.
method Theoretical analysis of Muon optimizer within the Lion-K family. result Muon implicitly solves an optimization problem enforcing spectral norm constraints.
Muon with Newton-Schulz converges to the same stationary point as SVD-polar, up to a constant factor.
problem Improving the convergence rate of Muon optimizer.
method Using Newton-Schulz steps for momentum orthogonalization, proving convergence rate and constant factor.
result Muon with Newton-Schulz converges to the same stationary point as SVD-polar, up to a constant factor.
MiMuon optimizer improves generalization for large models by reducing generalization error.
problem Improving generalization of Muon optimizer for large models.
method Enhanced Muon optimizer using orthogonalization of gradient, proving lower generalization error.
result MiMuon optimizer has a lower generalization error of O(N1) compared to Muon's O(NκT1). EF21-Muon optimizes deep learning with error feedback, improving efficiency and accuracy.
problem Lack of principled distributed frameworks for non-Euclidean LMO-based optimizers.
method Introduces EF21-Muon, a communication-efficient, non-Euclidean LMO-based optimizer with convergence guarantees.
result First efficient distributed implementation of non-Euclidean LMO-based optimizers, achieving up to 7x communication savings.
Muon replaces matrix gradient with polar factor, optimizing flat spectrum updates
problem Optimization bias in matrix updates
method Using polar factor of gradient
result Muon update maximizes entropy among bounded updates
Develops a gradient flow for Muon optimizer, a method for optimization.
problem Optimization of complex systems with matrix-valued parameters.
method Gradient flow on probability measures induced by regularized Muon optimizer.
result Derives continuous-time limits and proves Hamiltonian dissipation.
Muon optimizes training efficiency by improving data retention at large batch sizes.
problem Improving training efficiency and data retention at large batch sizes.
method Introducing Muon, a second-order optimizer, and combining it with muP for efficient hyperparameter transfer.
result Muon outperforms AdamW in retaining data efficiency at large batch sizes, enabling more economical training.
New Muon and Momo variants improve neural network optimization robustness.
problem Improving neural network optimization methods.
method Systematic exploration of non-Euclidean gradient descent variants.
result Momo variants of Muon are more robust to hyperparameter tuning.
TomOpt optimizes muon detector designs using differentiable programming.
problem Designing efficient particle detectors for muon tomography.
method Differentiable programming for muon interaction modeling, inference, and optimisation.
result Demonstrated end-to-end differentiable and inference-aware optimisation of particle physics instruments.
Muon optimizer improves federated learning performance.
problem Improving federated learning performance with Muon optimizer.
method Proposed FedMuon algorithm with orthonormalized update direction.
result FedMuon's learning rate is independent of problem-specific parameters.
Shampoo achieves higher token efficiency than Muon in language models.
problem Understanding the relationship and relative data efficiency of Shampoo and Muon compared to Adam and Signum.
method Extensive experiments on language models, demonstrating Shampoo's higher efficiency and decomposing its updates.
result Shampoo's benefits are attributed to its application to weight matrices, challenging interpretations based on variance adaptation and whitening.
New analysis of Muon and SignSGD on matrix-valued least squares problems.
problem Understanding the behavior of Muon and SignSGD on matrix-valued least squares problems.
method Derive explicit deterministic dynamics to study learning behavior of Muon and SignSGD.
result Muon and SignSGD exhibit different optimal learning rates and convergence characteristics based on batch size and data covariance.
Muon spectral optimizer outperforms SGD in associative memory tasks.
problem Understanding the advantage of spectral optimizers in learning associative memory.
method Linear associative memory problem, Gaussian inputs and outputs, power law frequency distribution, thresholded gradient approximation.
result Muon significantly outperforms SGD in storage capacity and recovery rates.
Study shows momentum-based optimizers like Muon and MomentumGD bias towards KKT points in smooth homogeneous models.
problem Understanding the implicit bias of momentum-based optimizers on smooth homogeneous models.
method Analysis of Muon, MomentumGD, Signum, and Adam optimizers under decaying learning rate schedules.
result Momentum-based optimizers approximate steepest descent trajectories and bias towards KKT points of margin maximization problems.
Unified view of Lion and Muon as Stochastic Frank-Wolfe methods.
problem Optimization of constrained problems in deep learning.
method Interpreting Lion and Muon as Stochastic Frank-Wolfe methods and extending the approach to heavy-tailed noise.
result Convergence guarantees and KKT point convergence for Lion and Muon.
Muon optimizes Transformer training with heavy-tailed data, achieving optimal sample complexity.
problem Theoretical understanding of non-Euclidean optimisation methods for heavy-tailed data in training Transformers.
method Addressing the gap in theoretical understanding, we show Muon achieves optimal sample complexity under heavy-tailed noise.
result Muon finds an ε-stationary point in nuclear norm with optimal sample complexity, absorbing heavy-tailed noise without dimension dependence.
Muon dynamics study uses spectral Wasserstein flow for optimization stability.
problem Optimizing deep learning models with gradient normalization.
method Introduces Spectral Wasserstein distances for matrix flows, proving equivalence with Benamou--Brenier formulation.
result Gradient-flow interpretation of mean-field normalized training dynamics.
MuonEq improves training of matrix-valued parameters by rebalancing momentum before orthogonalization.
problem Training matrix-valued parameters with orthogonalized-update optimizers like Muon.
method MuonEq introduces three lightweight pre-orthogonalization equilibration schemes: two-sided row/column normalization (RC), row normalization (R), and column normalization (C).
result Row/column normalization acts as a zeroth-order surrogate for whitening and improves the geometry seen by orthogonalization.
Muons and random optimizers perform similarly, challenging geometric optimization theory.
problem Empirical success of Muon optimizer challenges geometric optimization theory.
method Introducing Freon and Kaon optimizers, demonstrating performance without precise geometric structure.
result Performance of optimizers is controlled by alignment and descent potential, not geometric structure.
Drop-Muon updates only some layers, speeding up training.
problem Conventional deep learning optimizers update all layers at once, which can be inefficient.
method Drop-Muon updates only a subset of layers per step, with randomized schedules.
result Drop-Muon achieves up to 1.4x faster training time with similar accuracy.
New optimizer MARS-M combines variance reduction with Muon for faster LLM training.
problem Training large-scale neural networks efficiently.
method Integrates MARS variance reduction with Muon optimizer.
result MARS-M converges to a first-order stationary point at a rate of ildeO(T−1/3). AuON is a linear-time optimizer that improves upon Muon's performance without approximate orthogonal matrices.
problem High memory and computational costs of orthogonal momentum updates.
method AuON uses normalized nonlinear scaling and a 'emergency brake' to handle exploding attention logits.
result AuON achieves strong performance without approximate orthogonal matrices, preserving structural alignment and reconditioning.
Nuclear magnetic resonance (NMR) spectroscopy exploits the magnetic properties of atomic nuclei to discover the structure, reaction state and chemical environment of molecules. We propose a probabilistic generative model and inference procedures for NMR spectroscopy. Specifically, we use a weighted sum of trigonometric…
PolarGrad optimizes deep learning models by considering matrix structure, outperforming Adam and Muon.
problem Efficient optimization of large-scale neural networks and language models.
method A unifying framework for analyzing matrix-aware preconditioned methods, including PolarGrad.
result PolarGrad outperforms Adam and Muon in various tasks.
AI enhances cancer diagnostics using spectroscopy.
problem Early and accurate cancer diagnosis.
method Combining AI with spectroscopy-based techniques.
result AI improves cancer diagnostics speed and safety.
Improved spectroscopy classification with deep learning and synthetic data.
problem Identifying chlorinated solvents in Raman spectra.
method Locally-connected neural network (NN) for binary classification, autoencoder-based outlier detection, and synthetic training data.
result The proposed method outperforms existing algorithms in accuracy and robustness.
This work uses neural density estimation to analyze laser-induced breakdown spectroscopy data, enabling accurate predictions and uncertainty quantification.
problem Inference of probability densities in high-dimensional spectral data is often intractable.
method Normalizing flows on structured spectral latent spaces for density estimation and uncertainty quantification.
result The approach enables generation of realistic spectral samples and accurate prediction of state vectors with well-calibrated uncertainties.
Muon optimizes deep learning models on imbalanced data by learning all components equally.
problem Generalization issues in deep learning models on imbalanced data.
method Introduced Spectral Gradient Descent (SpecGD) as a canonical form of Muon and Shampoo, and studied its performance on imbalanced data.
result SpecGD learns all principal components of imbalanced data at equal rates, unlike vanilla GD which prioritizes dominant components.
Develops a Bayesian non-parametric approach for signal separation with varying components.
problem Signal separation with varying components across different input locations.
method Augments Gaussian Process Latent Variable Models with weighted sums of pure component signals and incorporates priors for linear weights.
result Framework allows for non-linear variations in signals and incorporates useful priors for linear weights.
Nuclear magnetic resonance (NMR) spectroscopy is one of the leading techniques for protein studies. The method features a number of properties, allowing to explain macromolecular interactions mechanistically and resolve structures with atomic resolution. However, due to laborious data analysis, a full potential of NMR …
Improved tensor GLM estimation for complex data.
problem Complex tensor data in GLMs leads to high-dimensional, ill-posed estimation.
method Proposed LSRTR-M algorithm using Muon updates for faster convergence and lower errors.
result LSRTR-M converges faster and achieves lower errors than LSRTR.
High-dimensional spectroscopy data makes ML models achieve near-perfect accuracy, even when chemical distinctions are absent.
problem Why machine learning models achieve near-perfect accuracy in spectroscopic classification tasks without chemically meaningful features.
method Theoretical analysis grounded in the Feldman-Hajek theorem and concentration of measure, combined with specific experiments on synthetic and real fluorescence spectra.
result Infinitesimal distributional differences in high-dimensional spaces can lead to perfect separability, making models achieve near-perfect accuracy in spectroscopy.
A new Riemannian framework optimizes LoRA for faster convergence and better performance.
problem Optimizing low-rank adapters in neural networks to improve convergence and performance.
method Integrates Riemannion optimizer, LoRA initialization, and efficient implementation for geometrically treating low-rank adapters.
result Consistent and noticeable improvements in convergence speed and final task performance over standard LoRA and its modifications.
Dynamic Time Warping improves regression accuracy on spectroscopy data.
problem Improving regression accuracy on spectroscopy data with DTW when data is across multiple wavelengths.
method Illustrated DTW's effectiveness on spectroscopy time-series data, showing its benefits in improving regression accuracy when only a single wavelength is considered. DTW combined with k-Nearest Neighbour reveals similarities and differences at the time-series level.
result DTW improves regression accuracy on spectroscopy data, especially when considering a single wavelength.
Active learning improves neutron spectroscopy experiments by automating measurement selection.
problem Efficiently searching for signals in neutron scattering experiments with limited beam time.
method Probabilistic active learning using log-Gaussian processes.
result Automated selection of informative measurements improves experimental efficiency.
This work uses Sylvester normalizing flows for more accurate metabolite quantification in MRS.
problem Challenges in accurate metabolite quantification in MRS due to spectral overlap, low SNR, and artifacts.
method Bayesian inference framework with physics-informed Sylvester normalizing flows.
result Accurate metabolite quantification, well-calibrated uncertainties, and insights into parameter correlations and multi-modal distributions.
The spectroscopy measurement is one of main pathways for exploring and understanding the nature. Today, it seems that racing artificial intelligence will remould its styles. The algorithms contained in huge neural networks are capable of substituting many of expensive and complex components of spectrum instruments. In …
Optimizes tensor completion using geodesics on Segre manifolds.
problem Incomplete tensor data in recommender systems and spectroscopy.
method Riemannian conjugate gradient optimization with explicit geodesic expressions.
result Recovery of tensor decomposition from as little as 10% of data.
The study analyzes convergence of adaptive optimizers under low-precision training.
problem Understanding why low-precision training remains effective for large models.
method Developed a theoretical framework for analyzing convergence of adaptive optimizers under floating-point quantization.
result Adaptive optimizers retain convergence rates close to full-precision methods under logarithmic mantissa scaling.
RAMANMETRIX simplifies Raman spectroscopy data analysis.
problem Complexity of Raman spectroscopy data processing.
method User-friendly software with chemometric analysis workflow.
result Facilitates integration of Raman spectroscopy into clinical routines.
Currently there is no validated objective measure of pain. Recent neuroimaging studies have explored the feasibility of using functional near-infrared spectroscopy (fNIRS) to measure alterations in brain function in evoked and ongoing pain. In this study, we applied multi-task machine learning methods to derive a pract…
Gluon optimizes LMO-based methods for large-scale tasks, improving performance and theory-practice gap.
problem LMO-based methods lack theoretical support for practical implementation and smoothness assumptions.
method Introduces Gluon, a new LMO-based method with refined smoothness model.
result Gluon's theoretical stepsizes match fine-tuned values, closing the theory-practice gap.