Improved sampling efficiency for molecular systems using path gradients after Flow Matching.
problem Improving sampling efficiency for complex molecular systems.
method Hybrid approach combining Flow Matching and path gradients.
result Up to a threefold increase in sampling efficiency for molecular systems.
Gradient matching method improves domain generalization across various datasets.
problem Machine learning's inability to generalize to unseen domains.
method Inter-domain gradient matching objective and first-order algorithm Fish.
result Fish method produces competitive results and surpasses baselines on 4 datasets.
Improves sample efficiency in RL by matching model-based gradients.
problem Lack of sample efficiency in model-free RL.
method Gradient matching between model-based and model-free RL components.
result Improves sample efficiency without increasing asymptotic bias.
New bounds show BBVI's gradient variance matches SGD conditions, improving parameterization efficiency.
problem Understanding and improving the convergence of black-box variational inference (BBVI).
method Showed BBVI satisfies matching gradient variance bounds corresponding to the ABC condition for smooth and quadratically-growing log-likelihoods.
result Proven BBVI's gradient variance matches SGD conditions, with superior dimensional dependence for mean-field parameterization.
New meta-learning method improves domain generalization by balancing parameters closer to domain centroids.
problem Improving domain generalization by reducing overfitting to specific domains.
method Arithmetic meta-learning with arithmetic-weighted gradients to balance parameters closer to domain centroids.
result Experimental validation of improved domain generalization performance.
We introduce a novel paradigm for learning non-parametric drift and diffusion functions for stochastic differential equation (SDE). The proposed model learns to simulate path distributions that match observations with non-uniform time increments and arbitrary sparseness, which is in contrast with gradient matching that…
The paper addresses statistical inference in matching markets with dependent missingness.
problem Statistical inference for two-sided matching markets with matching-induced dependence.
method Non-convex algorithm based on Grassmannian gradient descent, debiasing and projection framework.
result Near-optimal entrywise convergence rates for various matching mechanisms.
New methods distill data for deep networks efficiently.
problem Reduction of training data cost and inconvenience.
method Generative teaching networks, gradient matching, Implicit Function Theorem.
result New methods are computationally more efficient and improve model performance.
The paper establishes bounds for score-matching in causal discovery and generative modeling.
problem Estimating causal relationships from data.
method Training a deep neural network to estimate the score function and applying it to causal discovery.
result Bounds on the error rate of causal discovery methods using score-matching.
Score matching errors are not sufficient for measuring diffusion model quality.
problem The L2 score matching error is not a reliable measure of diffusion model performance. method Decomposed score errors into gradient and solenoidal components and analyzed their geometric properties.
result Only the gradient component of the score error affects the marginal distributional quality.
A new method for estimating uncertainties in neural ODEs without numerical integration.
problem Accurate estimation of predictive uncertainties in neural ODEs.
method Distributional Gradient Matching (DGM) algorithm that jointly trains a smoother and a dynamics model.
result Significantly more accurate predictions compared to traditional methods.
WaveGrad generates high-fidelity audio using gradient estimation.
problem Generating high-fidelity audio efficiently.
method Conditional model using score matching and diffusion models, iteratively refining a Gaussian white noise signal.
result WaveGrad can generate high-fidelity audio samples using as few as six iterations.
Extends dimension reduction to data-driven settings without gradients.
problem Gradient-based dimension reduction limitations in data-driven settings.
method Score ratio matching framework, tailored parameterization, regularization, eigenvalue deflation.
result Outperforms standard score-matching for problems with low-dimensional structure.
QAM uses adjoint matching to optimize continuous-action RL policies efficiently.
problem Efficient optimization of expressive diffusion or flow-matching policies with respect to a Q-function.
method QAM leverages adjoint matching to bypass the numerical instability of backpropagation through multi-step denoising processes.
result QAM consistently outperforms prior approaches on hard, sparse reward tasks in offline and offline-to-online RL.
Paper solves k-sparse parity problem with sign SGD, matching SQ lower bound.
problem Solving k-sparse parity problems efficiently.
method Sign stochastic gradient descent on neural networks.
result Matches Statistical Query lower bound for solving k-sparse parity problems.
GFM models neural network training as a dynamical system to forecast final weights.
problem Computational intensity and inefficiency in training deep neural networks.
method Gradient Flow Matching (GFM) treats training as a dynamical system with learned vector fields.
result GFM achieves forecasting accuracy competitive with Transformer-based models and significantly outperforms classical baselines.
Unified approach to domain generalization by aligning gradients and Hessians.
problem Developing models that generalize well across unseen domains.
method Moment Alignment, extending transfer measure to DG, aligning derivatives across domains.
result Moment Alignment unifies gradient and Hessian matching approaches, improving generalizability.
Gradient matching is a promising tool for learning parameters and state dynamics of ordinary differential equations. It is a grid free inference approach, which, for fully observable systems is at times competitive with numerical integration. However, for many real-world applications, only sparse observations are avail…
Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This inconsistence of gradient magnitude across different layers renders optimization of deep …
Heuristic weighting improves denoising score matching without requiring noise distribution assumptions.
problem Improving denoising score matching without assuming noise distribution.
method Demonstrated heteroskedasticity, derived optimal weighting functions, and provided theoretical and empirical comparisons.
result Heuristical weighting function can achieve lower variance than optimal weighting, facilitating more stable and efficient training.
New geometric analysis shows L2 score error is flawed for diffusion models.
problem Score matching errors in diffusion models do not fully capture distributional quality.
method Decomposed score errors into gradient and solenoidal components, focusing on gradient's role in Fokker-Planck dynamics.
result Only gradient component affects marginal distributional quality; solenoidal component is structurally invisible.
Efficiently approximates higher-order derivatives for generative models.
problem Expensive computation of higher-order derivatives in generative models.
method Rewrite SM objective in terms of directional derivatives and use finite difference for efficient approximation.
result Comparable results to gradient-based methods but significantly more computationally efficient.
Gradient matching method estimates implicit regularization in complex deep learning systems.
problem Estimating implicit regularization in modern deep learning systems with complex modifications.
method Gradient matching methods to empirically estimate implicit regularization.
result Empirical estimation of implicit regularization in arbitrary networks, including dropout.
GMC benchmark isolates retrieval in Transformers, revealing max-margin alignment.
problem Understanding how Transformers develop match-and-copy behavior on natural data.
method Introducing Gaussian Match-and-Copy (GMC) as a minimalist benchmark.
result Gradient descent drives parameters to diverge while aligning with max-margin separator.
Novel PCA method for high-dimensional inverse problems.
problem Optimizing large-scale random fields with gradient information.
method Gradient-Sensitive Principal Component Analysis (Gradient-SPCA) that modifies PCA using objective function gradients.
result Improvements in encoding quality for objective function minimization and field distribution.
SkMM selects data for finetuning by balancing bias and variance.
problem Balancing bias and variance in high-dimensional finetuning.
method Gradient sketching for bias reduction and moment matching for variance reduction.
result Gradient sketching selects samples efficiently and accurately.
PropEn uses matching to create a larger dataset for efficient design optimization.
problem Limited data and complex landscapes in scientific applications.
method PropEn uses a matching approach to implicitly guide design without a discriminator.
result PropEn efficiently approximates the gradient of property improvement within the data distribution.
Method infers parameters in complex diffusion processes.
problem Parameter inference in high-dimensional, non-linear diffusion processes.
method Differentiable score matching to approximate diffusion bridges, used in an importance sampler.
result Numerically stable framework for parameter inference and diffusion mean estimation.
New lower bounds for gradient methods in strongly convex finite-sum optimization.
problem Developing tight lower bounds for randomized gradient methods in finite-sum optimization.
method Deriving tight lower complexity bounds for SAG, SAGA, SVRG, SARAH, and related methods.
result Tight matches between lower bounds and upper bounds for various methods under specific conditions.
New approach to sparse optimal transport for matching tokens with experts.
problem Sparse matching of tokens with experts in neural networks.
method Sparsity-constrained optimal transport with cardinality constraints.
result Solves nonconvex cardinality constraints with gradient methods.
Paper tackles distribution matching by partially matching distributions, achieving robust results.
problem Robustly aligning two probability distributions.
method Developed a partial Wasserstein adversarial network (PWAN) to efficiently approximate the partial Wasserstein-1 (PW) discrepancy.
result The PWAN effectively produces highly robust matching results, outperforming state-of-the-art methods.
Kernel-Gradient Drifting improves generative modeling for non-Euclidean data.
problem Challenges in generative modeling for non-Euclidean data.
method Replaces Euclidean displacement with kernel-induced directions, exposing score-based structure.
result Kernel-gradient drifting enables state-of-the-art one-step generation for non-Euclidean data.
Researchers use discrete Morse theory to improve the topology of matching complexes of complete graphs.
problem Understanding the topology of matching complexes of complete graphs, especially for small n.
method Developed gradient vector fields to simplify the computation of homology groups.
result Computed the homology groups of M7 efficiently and conjectured an optimal gradient vector field. Large learning rates prevent memorization in denoising score matching.
problem Memorization of training data in diffusion-based generative models.
method Investigating the role of large learning rates in the small-noise regime, proving that they prevent convergence to the empirical optimal score.
result Large learning rates prevent memorization by making it impossible for the learned score to be arbitrarily close to the empirical optimal score.
This work classifies SOC loss functions based on their gradient properties.
problem Optimizing noisy systems in stochastic optimal control.
method Grouping loss functions into classes with the same gradient expectation.
result Different loss functions have the same optimization landscape but differ in gradient variance.
Inspired by the seminal work on Stein Variational Inference and Stein Variational Policy Gradient, we derived a method to generate samples from the posterior variational parameter distribution by \textit{explicitly} minimizing the KL divergence to match the target distribution in an amortize fashion. Consequently, we a…
New algorithms optimize without tuning, matching tuned SGD performance.
problem Optimizing machine learning models without manual hyperparameter tuning.
method Formalizes tuning-free algorithms for matching SGD performance with loose hints.
result Tuning-free algorithms can match SGD performance, but not optimal convergence rates.
Gradient matching with Gaussian processes is a promising tool for learning parameters of ordinary differential equations (ODE's). The essence of gradient matching is to model the prior over state variables as a Gaussian process which implies that the joint distribution given the ODE's and GP kernels is also Gaussian di…
New bounds show SGD can match deterministic gradient descent's convergence rate.
problem Optimizing SGD convergence rate under strong convexity and smoothness.
method Computer-aided Lyapunov analysis, focusing on bias-optimal bounds.
result SGD achieves optimal convergence rate in bias terms for a wide range of step-sizes.
Paper proves convergence of measure transfer schemes using slicing and matching.
problem Iterative schemes for measure transfer and approximation problems.
method Slicing-and-matching procedure, stochastic gradient descent on Wasserstein space.
result Almost sure convergence proof for stochastic slicing-and-matching schemes.
Matching pursuit algorithms are an important class of algorithms in signal processing and machine learning. We present a blended matching pursuit algorithm, combining coordinate descent-like steps with stronger gradient descent steps, for minimizing a smooth convex function over a linear space spanned by a set of atoms…
A new variational inference method using Gaussian score matching.
problem Approximating posterior distributions in Bayesian statistics.
method Score matching principle applied to variational inference.
result Gaussian score matching VI (GSM-VI) is faster and requires fewer gradient evaluations.
STORM-PG uses momentum for faster policy gradient updates.
problem Improving policy gradient methods for reinforcement learning.
method Introduces STORM-PG, a SARAH-based algorithm with exponential moving average.
result Achieves O(1/ε3) sample complexity, matching best-known rate. Many problems at the intersection of combinatorics and computer science require solving for a permutation that optimally matches, ranks, or sorts some data. These problems usually have a task-specific, often non-differentiable objective function that data-driven algorithms can use as a learning signal. In this paper, w…
New method aligns diffusion models for inference-time properties without retraining.
problem Aligning pre-trained diffusion models for desired inference-time properties.
method Variationally stable Doob's matching for provable guidance estimation.
result Consistent estimator of guidance with non-asymptotic convergence guarantees.
A higher-order Runge-Kutta optimizer performs poorly compared to Adam when evaluated fairly.
problem Evaluating the performance of adaptive Runge-Kutta optimizers under strict conditions.
method Built and evaluated a representative Adam variant using a Bogacki-Shampine 3(2) RK pair, FSAL reuse, and local-error step control.
result The adaptive nature of the RK optimizer is illusory; it behaves like a fixed-step optimizer with gradient averaging.
Backpropagation-free trunk training improves model performance on various benchmarks.
problem Memory inefficiency and noisy gradient estimates in deep network training.
method Split Forward Gradient (Split-FG) method that splits network into trunk and head, estimating only trunk gradient.
result Split-FG achieves better performance than pure forward-gradient training and backpropagation on various benchmarks.
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