AWP improves robustness by flattening weight loss landscape.
problem Improving robustness of deep neural networks against adversarial examples.
method Explicitly regularizes the flatness of weight loss landscape through adversarial weight perturbation.
result AWP forms a double-perturbation mechanism in adversarial training, leading to flatter weight loss landscape.
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.
Researchers improve NCE by addressing its flat loss landscape issues.
problem NCE's poor performance due to an ill-behaved loss landscape.
method Introduced eNCE with an exponential loss and normalized gradient descent.
result Proven that landscape issues arise from inappropriate noise distribution.
fSGLD optimizes deep learning by favoring flat regions in the loss landscape.
problem Understanding and improving the behavior and generalization of deep learning algorithms.
method Flatness-Aware Stochastic Gradient Langevin Dynamics (fSGLD) that biases learning towards flat basins.
result fSGLD targets a flatness-biased Gibbs distribution with explicit excess risk guarantees.
Neural networks' optimization dynamics are confined to a single basin despite connected basins in the loss landscape.
problem Neural networks' optimization dynamics are confined to a single basin despite connected basins in the loss landscape.
method Identifying entropic barriers arising from the interplay between curvature variations along low-loss paths and noise in optimization dynamics.
result Curvature-induced entropic forces bias noisy dynamics back toward the endpoints, explaining the confinement and connectivity of solutions.
Study geometric properties of loss functions to understand neural network performance.
problem Understanding the geometric properties of high-dimensional loss functions to improve neural network performance.
method Combine concepts from high-dimensional probability and differential geometry to study curvature properties in lower-dimensional loss representations.
result Mean curvature in the original loss space determines if saddle points appear as minima, maxima, or flat regions.
Looped transformers outperform standard transformers in complex reasoning tasks due to a specific loss landscape geometry.
problem Understanding why looped transformers outperform standard transformers in complex reasoning tasks.
method Explained through loss landscape geometry, distinguishing between U-shaped and V-shaped valleys, and proposing SHIFT training strategy.
result Looped transformers' recursive architecture induces a River-V-Valley landscape, leading to better loss convergence and complex pattern learning.
DPlis improves privacy in deep learning models by smoothing loss functions.
problem Privacy leakage in deep learning models trained on private data and low model performance.
method DPlis constructs a smooth loss function to favor noise-resilient models.
result DPlis effectively boosts model quality and training stability under privacy constraints.
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, …
New model shows SGD can prefer sharp or flat solutions based on label noise.
problem Understanding SGD's preference for flat or sharp solutions during training.
method Solved an analytically solvable model to explore SGD behavior.
result Data distribution determines sharpness at convergence; isotropic label noise leads to flat minimum preference.
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.
We analyze numerically the training dynamics of deep neural networks (DNN) by using methods developed in statistical physics of glassy systems. The two main issues we address are (1) the complexity of the loss landscape and of the dynamics within it, and (2) to what extent DNNs share similarities with glassy systems. O…
Variational quantum computing faces a flat optimization landscape problem.
problem Barren Plateaus (BP) in optimization landscapes.
method Theoretical and heuristic methods to understand and mitigate BPs.
result All algorithm components can lead to BPs if not well-suited.
Adversarial training makes logistic regression weight loss landscapes sharper.
problem Understanding why adversarial training sharpens the weight loss landscape in logistic regression.
method Theoretical analysis of linear logistic regression model with L2 norm constraints, and experiments on ResNet18.
result Adversarial training sharpens the weight loss landscape in linear logistic regression models.
New approach connects quantum phases to VQA trainability, enabling better scaling.
problem Scalability issues in VQAs, especially barren plateaus.
method Analog VQA ansätze composed of quenches of a disordered Ising chain, tuning disorder strength.
result Thermalized and MBL phases reach maximal expressivity at large M, but barren plateaus emerge at smaller M in the thermalized phase. DEO uses gradient information to escape saddle points in neural networks.
problem Training deep neural networks struggles with flat regions and saddle points.
method Dimer-Enhanced Optimization (DEO) uses gradient information to estimate curvature and escape saddle points.
result DEO improves training efficiency and performance compared to standard first-order methods.
We analyze the optimization landscape of α-loss in logistic models.
problem Optimization landscape of α-loss in logistic models.
method Tools from strictly-locally-quasi-convex functions and geometric techniques.
result Evolution of optimization landscape with respect to α.
Deeper models have a more favorable optimization landscape, making them more robust to noise.
problem Characterizing the effect of depth on the optimization landscape of linear regression models.
method Robust and over-parameterized setting, simple sub-gradient method.
result A simple sub-gradient method converges to a balanced solution that is close to the ground truth and enjoys a flat local landscape.
EpiMer merges models by solving Fréchet mean on a Riemannian manifold.
problem Integrating knowledge from multiple models without retraining.
method EpiMer casts model merging as solving the Fréchet mean on a Riemannian manifold, restricting computation to a low-rank subspace.
result EpiMer outperforms flat-geometry methods on image classification tasks.
Researchers improve visualization of neural network loss landscapes.
problem Understanding neural network generalization performance.
method Novel 'jump and retrain' procedure, non-linear dimensionality reduction (PHATE), computational homology.
result Improved visualization and quantification of neural network generalization performance.
Black holes offer insights into machine learning's loss landscapes.
problem Understanding the loss landscape in machine learning.
method Comparing machine learning loss landscapes to black hole entropy.
result Black holes provide an infinite family of potential landscapes with known minima.
Study visualizes actor-critic loss landscapes for inventory optimization.
problem Difficulties in solving multi-store dynamic inventory control problems.
method Low-dimensional visualizations of actor loss function.
result Loss landscapes favor optimal policies in reinforcement learning.
FP-BMA improves generalization by encouraging flat posteriors in Bayesian Model Averaging.
problem Lack of flat posterior in approximate Bayesian inference methods hinders effective Bayesian Model Averaging.
method Proposes Flat Posterior-aware Bayesian Model Averaging (FP-BMA) and Flat Posterior-aware Bayesian Transfer Learning schemes.
result FP-BMA successfully captures flat posteriors, improving generalization performance.
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.
Neural network training relies on our ability to find "good" minimizers of highly non-convex loss functions. It is well-known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and well-chosen training parameters (batch size, learning rate, optimizer) produce mi…
Analyzes adversarial training's impact on loss landscape, proposing PAS to improve model performance.
problem Challenges in optimizing models under adversarial training due to loss landscape properties.
method Analytical studies of adversarial loss functions, numerical analyses, PAS strategy.
result Adversarial training impairs optimization, but PAS strategy improves model performance.
Tilting loss functions improves machine learning performance.
problem Improving machine learning models, especially in under- and over-parameterized networks.
method Using evolving loss functions that emphasize different classes cyclically.
result Dynamical loss functions lead to better generalization and stability in training.
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.
Embedding principle explains loss landscape of deep neural networks.
problem Understanding the structure of loss landscapes in deep neural networks.
method Proposed an embedding principle that critical points of narrower DNNs can be embedded to critical points of wider DNNs.
result Wide DNNs are often attracted by highly-degenerate critical points embedded from narrower DNNs.
Many image processing tasks involve image-to-image mapping, which can be addressed well by fully convolutional networks (FCN) without any heavy preprocessing. Although empirically designing and training FCNs can achieve satisfactory results, reasons for the improvement in performance are slightly ambiguous. Our study i…
Study reveals sharp characterisation of local minima in neural network loss landscapes.
problem Characterizing local minima in high-dimensional two-layer ReLU neural networks.
method Exact low-dimensional representation of local minima using summary statistics and link with one-pass SGD dynamics.
result Local minima in overparameterized neural networks form discrete families with varying stability and reachability.
Deep ReLU networks with extra parameters have mostly good loss landscapes.
problem Finding good local minima in the loss landscape of deep neural networks.
method Analyzing shallow and deep ReLU networks with extra parameters on a generic dataset.
result Most activation patterns correspond to regions with no bad local minima.
This work justifies neural collapse under MSE loss and analyzes the optimization landscape.
problem Understanding neural collapse in deep neural networks under MSE loss.
method Global landscape analysis of vanilla nonconvex MSE loss.
result The only global minimizers are neural collapse solutions.
Novel approach embeds loss tunnels in neural networks, revealing insights into their structure.
problem Understanding the structure of neural network loss surfaces, especially low-loss tunnels.
method Directly embedding loss tunnels into the loss landscape of neural networks.
result Improved insights into the length and structure of loss tunnels, and better subspace inference in Bayesian neural networks.
Geodesics connect model modes in neural network loss landscapes.
problem Connecting modes in neural network loss landscapes.
method Reframed mode connectivity in Information Geometry, hypothesized geodesics as mode-connecting paths, proposed algorithm to approximate geodesics.
result Geodesics achieve mode connectivity in neural networks.
There are many surprising and perhaps counter-intuitive properties of optimization of deep neural networks. We propose and experimentally verify a unified phenomenological model of the loss landscape that incorporates many of them. High dimensionality plays a key role in our model. Our core idea is to model the loss la…
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.
SGD vs quasi-Newton optimization in neural networks: different landscapes, different generalizability.
problem Understanding neural network optimization and generalizability.
method Comparison of stochastic gradient descent (SGD) and quasi-Newton optimization methods using computational tools.
result SGD solutions are separated by lower barriers than quasi-Newton solutions, but quasi-Newton solutions are deeper and more isolated.
SmoothDARTS stabilizes DARTS-based architecture search by smoothing loss landscapes.
problem DARTS-based NAS methods suffer from instability, leading to deteriorating architectures.
method SmoothDARTS (SDARTS) uses perturbation-based regularization to smooth the loss landscape.
result SmoothDARTS improves the generalizability and performance of DARTS-based methods.
Paper explores challenges in training PINNs and loss landscape effects.
problem Challenges in training Physics-Informed Neural Networks (PINNs) due to loss landscape issues.
method Examined gradient-based optimizers Adam, L-BFGS, and their combination Adam+L-BFGS, and introduced NysNewton-CG (NNCG).
result Adam+L-BFGS outperforms other optimizers, and NysNewton-CG significantly improves PINN performance.
DASH improves ensemble generalizability by encouraging diverse, flat loss landscapes.
problem Improving generalization and robustness of deep ensembles.
method DASH promotes diversity and flatness in deep ensembles by encouraging base learners to move towards low-loss regions of minimal sharpness.
result DASH improves ensemble generalizability, as demonstrated by extensive empirical evidence.
Recent work has noted that all bad local minima can be removed from neural network loss landscapes, by adding a single unit with a particular parameterization. We show that the core technique from these papers can be used to remove all bad local minima from any loss landscape, so long as the global minimum has a loss o…
Reviews recent findings on neural network landscapes.
problem Non-convexity of loss functions causing bad landscapes.
method Rigorous geometric analysis and empirical exploration.
result Wide neural nets may have sub-optimal local minima.
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…
The study tests inferences about neural network optimization from linear interpolation of loss landscapes.
problem Understanding the difficulty of neural network optimization problems.
method Linear interpolation of neural network loss landscapes, systematic evaluation of various factors.
result Linear interpolation does not correlate with model performance, challenging prior intuition.
Large learning rates cause parameter instability, leading to better generalization.
problem Understanding why deep neural networks perform well despite operating outside the traditional stability regime.
method Analyzing the effect of large learning rates on the orientation of Hessian eigenvectors and parameter exploration.
result Large learning rates induce parameter instability, leading to better generalization through exploration of flatter regions of the loss landscape.
Deep learning dynamics exhibit anomalous superdiffusion initially, aiding escape from local minima.
problem Understanding the dynamics of learning in deep neural networks.
method Novel analysis of SGD dynamics and loss landscape structure.
result SGD exhibits anomalous superdiffusion initially, transitioning to subdiffusion as learning progresses.
The pursuit of explaining and improving generalization in deep learning has elicited efforts both in regularization techniques as well as visualization techniques of the loss surface geometry. The latter is related to the intuition prevalent in the community that flatter local optima leads to lower generalization error…