Regularizers change the geometric properties of loss functions in neural networks.
problem Understanding how different regularizers affect the geometric properties of loss functions in neural networks.
method Examined several regularizers, including weight decay, to determine if the regularized loss function becomes Morse.
result For certain regularizers, the regularized loss function becomes Morse, indicating a change in geometric properties.
Gradient descent implicitly follows regularization for general losses.
problem The implicit bias of gradient descent methods in machine learning.
method Empirical risk minimization over linear predictors with arbitrary convex, strictly decreasing losses.
result Gradient descent and regularization paths converge to the same direction for non-attained risks.
We demonstrate that almost all non-parametric dimensionality reduction methods can be expressed by a simple procedure: regularized loss minimization plus singular value truncation. By distinguishing the role of the loss and regularizer in such a process, we recover a factored perspective that reveals some gaps in the c…
Paper improves learning rates for GSC loss functions using iterated Tikhonov regularization.
problem Improving learning rates for GSC loss functions.
method Iterated Tikhonov regularization using proximal point method.
result Achieves fast and optimal rates for GSC loss functions.
We stabilize MI-based losses by adding a regularization term, improving their performance and stability.
problem Instability of MI-based losses in machine learning.
method Added a novel regularization term to stabilize MI-based losses.
result Regularization stabilizes training and improves the performance of MI-based losses.
Study uses property elicitation to understand how fairness regularizers affect optimal decisions.
problem Understanding how fairness regularizers change the optimal decision in predictive algorithms.
method Property elicitation to analyze the relationship between loss, regularization, and optimal decision.
result Necessary and sufficient condition for when a property changes with the addition of a regularizer.
The paper studies the loss landscape of regularized deep matrix factorization, revealing unique and sharp minimizers.
problem Understanding the loss landscape and minimizers of regularized deep matrix factorization problems.
method Theoretical analysis of ℓ2-regularized deep matrix factorization/deep linear network training problems with squared-error loss. result The unique end-to-end minimizer exists for all target matrices except for a set of Lebesgue measure zero.
New aggregation strategy handles unbounded losses with regret bounds.
problem Online optimization with unbounded loss functions.
method Follow The Regularized Leader (FTRL) with φ-divergence.
result Worst regret bound for unbounded losses with alternative divergences.
Gradient descent on ReLU networks with square loss implicitly favors balanced weights.
problem Understanding implicit regularization in nonlinear neural networks with regression losses.
method Analyzing gradient descent dynamics on ReLU networks with square loss.
result It is impossible to characterize the implicit regularization of ReLU networks with square loss by any explicit function of model parameters.
Paper introduces a new topological loss for better convergence.
problem Optimizing topological losses for model's desired topological behavior.
method Introduces a new regularized topology-aware loss function.
result Guarantees efficient optimization of the new loss function.
This study explores star-shaped regularizers learned from critic-based losses.
problem Understanding the structure of regularizers learned from critic-based losses.
method Optimizing critic-based loss functions over star-shaped regularizers.
result Derives exact expressions for optimal regularizers in certain cases.
Proposes PER loss to regularize neural network activations to normal distribution.
problem Improving neural network generalization and training speed.
method Regularizes activations to standard normal distribution via projected error function and Wasserstein distance.
result Minimizes Wasserstein distance between activation distribution and standard normal.
In this work, we study data preconditioning, a well-known and long-existing technique, for boosting the convergence of first-order methods for regularized loss minimization. It is well understood that the condition number of the problem, i.e., the ratio of the Lipschitz constant to the strong convexity modulus, has a h…
Regularized empirical risk minimization including support vector machines plays an important role in machine learning theory. In this paper regularized pairwise learning (RPL) methods based on kernels will be investigated. One example is regularized minimization of the error entropy loss which has recently attracted qu…
New approach uses hinge loss for iterative regularization in classification.
problem Improving classification accuracy through regularization.
method Develops an iterative regularization approach based on hinge loss.
result Proves convergence and rates of convergence for classification.
The paper introduces a new loss function to prevent overfitting in semi-supervised graph networks.
problem Overfitting in semi-supervised graph networks trained with cross-entropy loss.
method Proposes an unsupervised manifold smoothness loss to regularize the graph convolutional networks.
result Adding the proposed loss consistently improves performance of graph networks.
Evolutionary methods improve neural network loss functions, reducing overfitting.
problem Improving neural network performance and preventing overfitting.
method Evolutionary computation to optimize loss functions, balancing error pull and overfitting push.
result Evolved loss functions effectively reduce overfitting, leading to better performance and robustness.
Proposes a new regularization technique for neural networks using elliptic operators.
problem Improving model behavior in underrepresented data regions.
method Modifies the empirical risk minimization objective to minimize an elliptic operator over the data domain.
result The proposed regularization technique anticipates error behavior outside the training set using existing elliptic operator theory.
New model leads to optimal test loss in sparse linear regression.
problem Sparse linear regression with low test loss despite interpolating training data.
method Developed a new parametrization of the model that combines benefits of ℓ1 and ℓ2 norms.
result Training via gradient descent leads to an interpolator with near-optimal test loss.
Optimizing full likelihoods adapts loss scales and shapes for robust modeling.
problem Rigid loss functions limit model adaptability and robustness.
method Optimize full likelihoods with adjustable parameters.
result Adaptive tuning of loss scales and shapes improves model robustness.
A method to identify important features without solving the full problem.
problem Identifying important features in high-dimensional data.
method Persistent reduction using extreme ray identification on a polyhedral cone.
result A subset of features can be guaranteed to have zero coefficients in all optimal solutions.
Optimal sampling bounds for various classification losses under different regularization terms.
problem Achieving optimal sampling complexity for classification losses under different regularization terms.
method Proved optimal sampling bounds for a broad class of Lipschitz continuous classification loss functions under various regularization terms.
result Proved k2/ε2 upper and lower bounds for ∥⋅∥2/k regularization, and k/ε2 upper and lower bounds for ∥⋅∥1/k regularization. SGD with large learning rates can achieve better test accuracy than expected.
problem SGD with large learning rates often outperforms expected convergence bounds.
method Proved that SGD with small learning rates stays close to gradient flow path on modified loss.
result Explicitly adding an implicit regularizer to the loss improves test accuracy.
New method prevents neural network breakdown by combining trimmed loss and variation regularization.
problem Outlier contamination in neural network training.
method Integrates transformed trimmed loss and higher-order variation regularization.
result Ensures robustness to outlier contamination with a high functional breakdown point.
The use of convex regularizers allows for easy optimization, though they often produce biased estimation and inferior prediction performance. Recently, nonconvex regularizers have attracted a lot of attention and outperformed convex ones. However, the resultant optimization problem is much harder. In this paper, for a …
This paper analyzes M-estimators under infinite-variance noise in high dimensions.
problem High-dimensional M-estimation with infinite-variance noise.
method Study of the Fenchel conjugate domain and its impact on risk.
result Exact risk of M-estimators under infinite-variance noise is derived.
New algorithm ATENT improves adversarial robustness in neural networks.
problem Improving neural network robustness against adversarial attacks.
method Proposes a new loss function with entropic regularization for training robust neural networks.
result ATENT achieves competitive robust classification accuracy on benchmark datasets.
We consider the problem of supervised learning with convex loss functions and propose a new form of iterative regularization based on the subgradient method. Unlike other regularization approaches, in iterative regularization no constraint or penalization is considered, and generalization is achieved by (early) stoppin…
We show that the EH class and the LOSS invariant of Legendrian knots in contact 3-manifolds are functorial under regular Lagrangian concordances in Weinstein cobordisms. This gives computable obstructions to the existence of regular Lagrangian concordances.
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.
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.
The goal of regression and classification methods in supervised learning is to minimize the empirical risk, that is, the expectation of some loss function quantifying the prediction error under the empirical distribution. When facing scarce training data, overfitting is typically mitigated by adding regularization term…
Dropout is a simple but effective technique for learning in neural networks and other settings. A sound theoretical understanding of dropout is needed to determine when dropout should be applied and how to use it most effectively. In this paper we continue the exploration of dropout as a regularizer pioneered by Wager,…
Enhances trading metrics with financially grounded loss functions.
problem Challenges in financial deep learning, especially interpretability.
method Introduces loss functions derived from finance metrics and turnover regularization.
result Proposed loss functions outperform traditional methods in trading metrics.
The aim of this paper is to provide new theoretical and computational understanding on two loss regularizations employed in deep learning, known as local entropy and heat regularization. For both regularized losses we introduce variational characterizations that naturally suggest a two-step scheme for their optimizatio…
We consider the problem of learning a forest of nonlinear decision rules with general loss functions. The standard methods employ boosted decision trees such as Adaboost for exponential loss and Friedman's gradient boosting for general loss. In contrast to these traditional boosting algorithms that treat a tree learner…
This study connects Jacobian regularization to adversarial robustness and improves generalization.
problem Adversarial attacks make deep neural networks vulnerable.
method Developed a connection between Jacobian regularization and adversarial training, and established robust generalization gaps.
result Jacobian norms are related to both standard and robust generalization.
Recent years have seen adversarial losses been applied to many fields. Their applications extend beyond the originally proposed generative modeling to conditional generative and discriminative settings. While prior work has proposed various output activation functions and regularization approaches, some open questions …
Adam's hyperparameters implicitly regularize solutions, penalizing or impeding loss gradients' norms.
problem Implicit regularization in Adam's hyperparameters and training stage.
method Backward error analysis and ODE approximations to study Adam's behavior.
result Adam's implicit regularization depends on hyperparameters and training stage, involving different norms.
Deep networks can memorize random labels; symmetric loss improves this.
problem Deep networks can memorize random labels, ignoring standard regularization.
method Empirical studies with MNIST and CIFAR-10 datasets, formal definition of robustness.
result Symmetric loss function improves network's ability to resist memorization.
The paper proposes effective margin regularization to improve adversarial robustness in deep neural networks.
problem Adversarial vulnerability of deep neural networks (DNNs).
method Regularization of effective weight norm during training to maximize effective margins.
result Effective margin regularization (EMR) boosts adversarial robustness in both standard and adversarial training.
We propose and analyze a regularization approach for structured prediction problems. We characterize a large class of loss functions that allows to naturally embed structured outputs in a linear space. We exploit this fact to design learning algorithms using a surrogate loss approach and regularization techniques. We p…
Wasserstein distributionally robust optimization (DRO) has recently achieved empirical success for various applications in operations research and machine learning, owing partly to its regularization effect. Although connection between Wasserstein DRO and regularization has been established in several settings, existin…
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…
High-dimensional sparse modeling via regularization provides a powerful tool for analyzing large-scale data sets and obtaining meaningful, interpretable models. The use of nonconvex penalty functions shows advantage in selecting important features in high dimensions, but the global optimality of such methods still dema…
DNNs with L2 regularization reveal feature learning dynamics and sparsity.
problem Understanding feature learning in DNNs with L2 regularization. method Reformulating loss in terms of layerwise activations and covariances.
result Proving sparsity of local minima in L2-regularized DNNs. This paper is concerned with the factorization form of the rank regularized loss minimization problem. To cater for the scenario in which only a coarse estimation is available for the rank of the true matrix, an ℓ2,0-norm regularized term is added to the factored loss function to reduce the rank adaptively; and…
Gradient descent implicitly regularizes neural networks by penalizing large loss gradients.
problem How to optimize deep neural networks without explicit regularization.
method Backward error analysis to calculate implicit gradient regularization and demonstrate its effectiveness empirically.
result Implicit gradient regularization biases gradient descent toward flat minima, improving model robustness and test errors.