Stochastic Gradient Descent (SGD) and its variants are mainstream methods for training deep networks in practice. SGD is known to find a flat minimum that often generalizes well. However, it is mathematically unclear how deep learning can select a flat minimum among so many minima. To answer the question quantitatively…
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
48 results for “Flat Minima”
The notion of flat minima has played a key role in the generalization studies of deep learning models. However, existing definitions of the flatness are known to be sensitive to the rescaling of parameters. The issue suggests that the previous definitions of the flatness might not be a good measure of generalization, b…
Proposes NRS to find flat minima in deep neural networks.
problem Finding optimal solutions in deep neural networks with overparameterization.
method NRS leverages the concept of flat minima and uses Kullback-Leibler divergence to regularize the neighborhood region in weight space.
result NRS drives optimizers towards flat minima, improving generalization ability across various model architectures.
Zeroth-order methods favor flat minima in machine learning.
problem Finding solutions with small Hessian trace in optimization.
method Zeroth-order optimization with two-point estimator.
result Zeroth-order optimization converges to flat minima.
New bounds link flat minima to good generalisation in overparameterized models.
problem Understanding the relationship between flat minima and generalisation in overparameterized machine learning models.
method Combining PAC-Bayes, Poincaré, and Log-Sobolev inequalities to derive generalisation bounds involving gradient terms.
result Flat minima positively influence generalisation performance, highlighting the benefits of the optimisation phase.
Flat minima lead to better generalization in low-rank matrix recovery models.
problem Understanding why flat minima generalize well in overparameterized models.
method Analysis of overparameterized matrix and bilinear sensing, robust PCA, covariance matrix estimation, and neural networks with quadratic activation functions.
result Flat minima, measured by the trace of the Hessian, exactly recover the ground truth in low-rank matrix recovery models under standard statistical assumptions.
It is well known that (stochastic) gradient descent has an implicit bias towards flat minima. In deep neural network training, this mechanism serves to screen out minima. However, the precise effect that this has on the trained network is not yet fully understood. In this paper, we characterize the flat minima in linea…
New algorithms improve neural network generalization by finding flat minima.
problem Finding better generalization in neural networks through flat minima.
method Developed Entropy-SGD and Replicated-SGD algorithms to maximize flatness in the loss function.
result Consistently improved generalization error for various deep learning architectures.
New metric shows how different regularization methods affect deep linear networks.
problem Understanding the training dynamics of deep linear networks.
method Introduced a new metric called layer imbalance to analyze training dynamics. Demonstrated behavior of different regularization methods and stochastic gradient descent.
result Different regularization methods behave similarly, leading to a flat minima.
It has been empirically observed that the flatness of minima obtained from training deep networks seems to correlate with better generalization. However, for deep networks with positively homogeneous activations, most measures of sharpness/flatness are not invariant to rescaling of the network parameters, corresponding…
New results show flat minima in neural networks suffer from high dimensionality.
problem Flat minima in neural networks generalize poorly in high dimensions.
method Theoretical analysis of two-layer ReLU networks with multivariate inputs.
result Flat minima lead to exponentially slower convergence in high dimensions.
New research shows flat minima in robust loss landscapes correlate with good adversarial robustness.
problem Adversarial training leads to robust overfitting, poor robust generalization.
method Average- and worst-case metrics to measure flatness in robust loss landscapes.
result Flatness in robust loss landscapes correlates with good adversarial robustness.
Flat-minima optimizers improve neural network generalization.
problem Improving neural network generalization performance.
method Stochastic Weight Averaging (SWA) and Sharpness-Aware Minimization (SAM).
result Surprising findings from loss surface analysis and broad benchmarking.
Stochastic gradient descent with noise of machine learning type. Part II: Continuous time analysiscs.LG
Continuous-time analysis shows SGD with noise prefers flat minima.
problem Optimizing neural networks using SGD with noise.
method Continuous-time model for SGD with noise analysis.
result Optimization prefers flat minima in certain noise regimes.
S-SGD: Symmetrical Stochastic Gradient Descent with Weight Noise Injection for Reaching Flat Minimacs.LG
S-SGD adds symmetrical noise to weights to avoid sharp minima in deep learning.
problem SGD does not always converge to a flat minimum, leading to poor generalization.
method Symmetrical weight noise injection in SGD.
result S-SGD outperforms conventional SGD and weight-noise injection methods in large batch training.
New IF method improves accuracy in deep neural networks with noisy data.
problem Inaccurate influence estimates in deep neural networks, especially with noisy data.
method Established a connection between influence estimation error, validation set risk, and sharpness, introducing a novel estimation form for flat validation minima.
result Our novel Influence Function approach provides more accurate influence estimates, validated across various tasks.
This paper explains why Adam generalizes worse than SGD by analyzing its components.
problem Understanding why Adam generalizes worse than Stochastic Gradient Descent (SGD).
method Diffusion theoretical framework to disentangle the effects of Adaptive Learning Rate and Momentum.
result Adaptive Learning Rate helps escape saddle points but not select flat minima, while Momentum provides a drift effect to help pass through saddle points.
AMP regularization improves deep learning models by favoring flat minima.
problem Improving deep learning model generalization and avoiding overfitting.
method AMP regularization uses adversarial model perturbation to minimize a norm-bounded perturbation of the empirical risk.
result AMP regularization leads to state-of-the-art performance across various deep architectures.
Despite the non-convex nature of their loss functions, deep neural networks are known to generalize well when optimized with stochastic gradient descent (SGD). Recent work conjectures that SGD with proper configuration is able to find wide and flat local minima, which have been proposed to be associated with good gener…
G-TRACER optimizes deep learning by promoting flat minima.
problem Promoting generalization in deep learning architectures.
method Geometric TRACE Ratio regularization, curvature-regularized optimizers.
result Converges to a neighborhood of local minima of unregularized objective.
Study of SGD with state-dependent noise, improving escape from local minima.
problem Understanding and improving the dynamics of SGD in non-convex optimization.
method Formal study on SGD with state-dependent noise, proposing power-law dynamic with state-dependent diffusion.
result Power-law dynamic can escape from sharp minima exponentially faster than flat minima.
The alignment property of SGD noise and how it helps select flat minima: A stability analysisstat.ML
SGD noise helps select flat minima by concentrating in sharp directions and being proportional to loss value.
problem Understanding the implicit regularization of SGD and selecting flat minima in over-parameterized models.
method Relating SGD's linear stability to the Frobenius norm of the Hessian and analyzing the alignment property of SGD noise.
result Flat minima are linearly stable for SGD, and their sharpness is bounded independently of model size and sample size.
New rigidity results for critical metrics of a quadratic curvature functional.
problem Proving uniqueness of critical metrics for a specific curvature functional.
method Analyzing complete, possibly non-compact, critical metrics of the quadratic curvature functional.
result Critical metrics with finite energy are scalar flat (global minima) for dimensions n≥10.
Combining Adam and its Inverse Counterpart to Enhance Generalization of Deep Learning Optimizerscs.LG
DualAdam improves generalization of Adam by integrating its update mechanisms.
problem Adam's tendency to converge to sharp minima leading to suboptimal generalization.
method DualAdam combines Adam and inverse Adam's update mechanisms to enhance generalization.
result DualAdam outperforms Adam and state-of-the-art variants in generalization performance.
By using the viewpoint of modern computational algebraic geometry, we explore properties of the optimization landscapes of the deep linear neural network models. After clarifying on the various definitions of "flat" minima, we show that the geometrically flat minima, which are merely artifacts of residual continuous sy…
Flatness After All?cs.LG
Paper proposes a new flatness measure for neural networks to improve generalization.
problem Generalization in deep learning models, especially with overparameterization.
method Soft rank measure of the Hessian to assess flatness and generalization.
result Soft rank flatness measure accurately estimates generalization gaps for various models.
New approach ties loss curvature to model performance in deep learning.
problem Understanding the relationship between loss curvature and model performance in deep learning.
method Empirical analysis of loss Hessians and theoretical results on input-output Jacobians.
result Novel generalization bound in terms of empirical Jacobian.
SGD with constant stepsize converges to a non-Gaussian limit near flat minima.
problem Behavior of SGD near flat minima with convex objectives.
method Analyzes SGD with Markovian noise and contractive driving chain.
result Invariant law concentrates on scale and converges weakly to a non-Gaussian stationary distribution.
Gradient descent with noise converges to a unique optimum in nonconvex matrix factorization.
problem Gradient descent with noise converges to a unique optimum in nonconvex matrix factorization.
method A perturbed form of gradient descent with arbitrary initialization.
result Gradient descent with noise converges to a unique optimum.
The sharp, the flat and the shallow: Can weakly interacting agents learn to escape bad minima?stat.ML
An open problem in machine learning is whether flat minima generalize better and how to compute such minima efficiently. This is a very challenging problem. As a first step towards understanding this question we formalize it as an optimization problem with weakly interacting agents. We review appropriate background mat…
Training neural networks involves finding minima of a high-dimensional non-convex loss function. Knowledge of the structure of this energy landscape is sparse. Relaxing from linear interpolations, we construct continuous paths between minima of recent neural network architectures on CIFAR10 and CIFAR100. Surprisingly, …
mSAM improves generalization by making models flatter.
problem Over-parameterized models can have varying generalization performance.
method mSAM modifies loss function to favor flatter minima through adversarial perturbations.
result mSAM achieves flatter minima than SAM and SGD, improving generalization.
Enhances deep learning by boosting generalization and convergence.
problem Improving generalization and convergence in deep learning models.
method Implicit Regularization Enhancement (IRE) framework that decouples flat and sharp directions.
result IRE consistently improves generalization performance across various deep learning tasks and models.
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.
New framework learns sufficient invariant features robustly across distribution shifts.
problem Learning robust models under distribution shifts between training and test datasets.
method Sufficient Invariant Learning (SIL) framework and Adaptive Sharpness-aware Group Distributionally Robust Optimization (ASGDRO) algorithm.
result Empirical evaluations confirm ASGDRO's robustness against distribution shifts.
As we have proved in [L], the geodesic flows associated with the flat metrics on T^2 minimize the polynomial entropy. In this paper, we show that, among the geodesic flows that are Bott integrable and dynamically coherent, the geodesic flows associated to flat metrics are local strict minima for the polynomial entropy.…
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.
Paper finds exact Hessian sharpness in deep matrix factorization.
problem Understanding the geometry of loss landscapes in deep matrix factorization.
method Presented the first exact expression for Hessian maximum eigenvalue.
result Spectral-norm balance is a sufficient condition for flatness in deep matrix factorization.
Gradient-based methods find saddle points, not critical points, in neural networks.
problem Gradient-based optimization methods converge to saddle points rather than critical points in deep neural networks.
method Critical point-finding methods used to analyze neural network losses.
result Gradient-based methods often converge to or pass through gradient-flat regions, where gradient norm has a stationary point.
Understanding the behavior of stochastic gradient descent (SGD) in the context of deep neural networks has raised lots of concerns recently. Along this line, we study a general form of gradient based optimization dynamics with unbiased noise, which unifies SGD and standard Langevin dynamics. Through investigating this …
The Gibbs algorithm's generalization error is bounded, improving with prior volume in low temperatures.
problem Bounding the generalization error of the Gibbs algorithm in low temperature regimes.
method Analyzes the Gibbs algorithm's performance, extending known high-temperature bounds to low-temperature scenarios.
result With high probability, the generalization error decreases with the total prior volume of similar hypotheses.
Averaged SGD optimizes a smoothed objective, leading to better generalization.
problem Improving generalization performance in machine learning models.
method Analyzed the smoothed objective function of SGD and proved that averaged SGD can optimize this smoothed function efficiently.
result Averaged SGD can efficiently optimize a smoothed objective, leading to better generalization.
Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers without getting stuck in local critical points, and that such minimizers are often …
A new pruning method finds sparse minimizers in flat regions of deep neural networks.
problem Finding sparse minimizers in flat regions of deep neural networks.
method Directional pruning using an proximal gradient algorithm.
result Empirical results show promising sparsity (92%) and comparable minima to SGD.
This work explains GANs as Bayesian neural networks with partial stochasticity.
problem Challenges in optimizing GANs and understanding their limitations.
method Interpreting GANs as Bayesian neural networks with partial stochasticity, establishing conditions, and proposing strategies to smooth the loss landscape and find solutions with minimum description length.
result Proposed strategies lead to performance improvements and deeper understanding of GANs.
This work examines the stability of GD and SGD near minima, revealing nonlinear dynamics that differ from linear analysis.
problem The stability of optimization algorithms like GD and SGD near minima is not well understood.
method The authors derive an exact criterion for stable oscillations of GD near minima in the multivariate setting, considering high-order derivatives.
result Nonlinear dynamics can diverge in expectation even if a single batch is unstable, challenging linear analysis.
This research explains why SGD generalizes better than ADAM in deep learning.
problem Understanding the generalization gap between SGD and ADAM in deep learning.
method Analyzing local convergence behaviors through Levy-driven stochastic differential equations (SDEs).
result SGD is more locally unstable and better escapes from sharp minima to flatter ones, leading to better generalization.
We theoretically study the landscape of the training error for neural networks in overparameterized cases. We consider three basic methods for embedding a network into a wider one with more hidden units, and discuss whether a minimum point of the narrower network gives a minimum or saddle point of the wider one. Our re…