We analyze bias-variance of margin losses.
problem Understanding model overfitting/underfitting.
method Bias-variance decomposition for strictly convex margin losses.
result Expected risk decomposes into central model risk and data variation.
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “convex bias”
Study iterative regularization for linear models with convex bias, improving robust sparse recovery.
problem Improving robust sparse recovery with iterative regularization for linear models.
method Primal-dual gradient approach, analyzing convergence in presence of noise, combining regularization and optimization.
result Theoretical results show state-of-the-art performances with computational speed-ups.
Study shows SGD's generalization is not explained by implicit bias.
problem Explaining the generalization ability of overparameterized learning algorithms.
method Revisited Stochastic Convex Optimization with SGD, demonstrating limitations of implicit bias.
result No distribution-independent or distribution-dependent implicit regularizer can explain SGD's generalization.
The paper analyzes optimal implicit bias in linear regression for over-parameterized models.
problem Finding the best generalization performance in over-parameterized linear regression.
method Asymptotic analysis of generalization performance for convex functions/potentials.
result Optimal implicit bias that achieves the best generalization error under certain conditions.
An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Biasstat.ML
SGD's uncertainty quantified in non-convex learning problems.
problem Uncertainty quantification in non-convex learning problems.
method Asymptotic normality of SGD iterates and bias characterization.
result SGD iterates are asymptotically normally distributed around the expected value of the invariant distribution.
Unified framework approximates gradient descent's implicit bias in high dimensions.
problem Understanding gradient descent's behavior in overparameterized settings with convex losses.
method Unified framework for convex losses, including sensitivity analysis.
result Approximation of minimum-norm interpolation in high dimensions.
The paper improves convergence for linear systems using entropic mirror descent with Polyak stepsizes.
problem Convergence analysis for linear systems with unbounded domain.
method Entropic mirror descent with Polyak stepsizes, sublinear and linear convergence results.
result Generalized convergence result for arbitrary convex functions.
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.
New insights into bias mitigation show DRO isn't a complete solution.
problem Bias in machine learning systems across different data subsets.
method Theoretical analysis of Distributionally Robust Optimization (DRO) and data curation.
result Neither DRO nor data curation alone can fully address bias issues.
Scalable algorithm for computing Wasserstein-2 barycenters without bias.
problem Computing Wasserstein-2 barycenters efficiently and accurately.
method Input convex neural networks and cycle-consistency regularization.
result Our approach avoids introducing bias and does not require minimax optimization.
NNLMs optimize poorly for word probabilities due to embedding space structure.
problem NNLMs assign suboptimal probabilities to some words.
method Analyzed the inductive bias of NNLMs and the structure of word embeddings.
result Words on the convex hull have bounded probability, affecting others.
This paper analyzes SGD with biased gradients for deep learning models.
problem Analyzing SGD with biased gradients for deep learning models.
method Non-asymptotic analysis of SGD with adaptive steps for non-convex smooth functions.
result Adagrad, RMSProp, and AMSGRAD converge to critical points at a similar rate to unbiased case.
We found hidden convexity in FPCA and developed a faster algorithm.
problem Bias in PCA leading to unequal subgroup outcomes.
method Convex optimization via eigenvalue optimization.
result Faster and fairer PCA algorithm.
Paper proposes a new method to separate low rank and sparse matrices without bias.
problem Recovering low rank and sparse matrices from measurements.
method Uses nonconvex regularizers and alternating proximal gradient descent.
result Error bounds for the algorithm applied to sparse optimization, matrix completion, and robust PCA.
Self-attention optimizers converge to optimal weights, revealing bias patterns.
problem Understanding the implicit bias in self-attention mechanisms.
method Analysis of gradient-based optimization in self-attention layers.
result Adaptive step-size strategies can accelerate convergence to optimal weights.
Paper analyzes convergence of decentralized algorithms with noise and bias.
problem Finite time convergence analysis of decentralized stochastic approximation schemes.
method Separated iterates into consensual parts and consensus error; bounded consensus error in terms of stationarity.
result Decentralized SA scheme converges at rate.
New models reduce discrimination in machine learning without sacrificing explanatory bias.
problem Discrimination and explanatory bias in fairness measures.
method Causal effect estimators using propensity score analysis.
result Theoretical and practical superiority of FairCEEs over existing models.
Proposes EDM algorithm to accelerate model training in distributed networks.
problem Hindered effectiveness of distributed stochastic optimization algorithms due to data heterogeneity and network sparsity.
method Introduces Exact-Diffusion with Momentum (EDM) algorithm, incorporating momentum techniques to mitigate bias and enhance convergence rate.
result EDM algorithm converges sub-linearly to the optimal solution, radius independent of data heterogeneity, for non-convex objective functions.
GD at EoS edge minimizes logistic loss without monotonic convergence.
problem Understanding GD's implicit bias at the edge of stability.
method Theoretical analysis of logistic regression with constant stepsize GD.
result GD with any constant stepsize minimizes logistic loss over long time scales.
A number of recent work studied the effectiveness of feature selection using Lasso. It is known that under the restricted isometry properties (RIP), Lasso does not generally lead to the exact recovery of the set of nonzero coefficients, due to the looseness of convex relaxation. This paper considers the feature selecti…
Truncated backpropagation through time (TBPTT) is a popular method for learning in recurrent neural networks (RNNs) that saves computation and memory at the cost of bias by truncating backpropagation after a fixed number of lags. In practice, choosing the optimal truncation length is difficult: TBPTT will not converge …
Paper presents a new algorithm to approximate Wasserstein-2 barycenters without bias.
problem Approximating Wasserstein-2 barycenters of continuous measures.
method Generative model approach using arbitrary neural networks.
result The method does not introduce bias and is applicable to large-scale tasks.
Constant Step Size Least-Mean-Square: Bias-Variance Trade-offs and Optimal Sampling Distributionscs.LG
We consider the least-squares regression problem and provide a detailed asymptotic analysis of the performance of averaged constant-step-size stochastic gradient descent (a.k.a. least-mean-squares). In the strongly-convex case, we provide an asymptotic expansion up to explicit exponentially decaying terms. Our analysis…
Gradient descent stagnates in low-precision, but unbiased rounding schemes improve convergence.
problem Stagnation of gradient descent in low-precision computation.
method Proposed unbiased stochastic rounding schemes that trade zero bias for larger probability of preserving small gradients.
result Unbiased rounding methods typically improve convergence rate of gradient descent for convex problems.
With the purpose of examining biased updates in variance-reduced stochastic gradient methods, we introduce SVAG, a SAG/SAGA-like method with adjustable bias. SVAG is analyzed in a cocoercive root-finding setting, a setting which yields the same results as in the usual smooth convex optimization setting for the ordinary…
New attention model removes softmax, improving sequence length bias.
problem Softmax attention's limitations and sequence length bias.
method Replaces softmax with normalization in self-attention.
result Normalization leads to more robust and bias-free attention.
Polynomial-time convex optimization for CNNs with ReLU activations.
problem Training Convolutional Neural Networks (CNNs) with ReLU activations.
method Developed a convex analytic framework using semi-infinite duality to formulate equivalent convex optimization problems for CNN architectures.
result Proved that two-layer CNNs can be globally optimized via an norm regularized convex program.
Optimized AIS scheme reduces bias and MSE for general proposals.
problem Performing Monte Carlo integration with general proposals.
method Global optimization of χ²-divergence using stochastic gradient Langevin dynamics.
result Explicit theoretical guarantees for uniform-in-time MSE reduction.
The paper analyzes fluctuations in ensemble models in high-dimensional settings.
problem Understanding statistical fluctuations in ensemble models in high-dimensional settings.
method Develops a rigorous theory for the study of fluctuations in ensemble of generalised linear models.
result Provides a complete description of the asymptotic joint distribution of the empirical risk minimizer for convex losses in high-dimensional settings.
Recently, there has been focus on penalized log-likelihood covariance estimation for sparse inverse covariance (precision) matrices. The penalty is responsible for inducing sparsity, and a very common choice is the convex norm. However, the best estimator performance is not always achieved with this penalty. The …
This thesis tackles non-convex Bayesian learning via scalable dynamic importance sampling algorithms.
problem Non-convex Bayesian learning problem in deep neural networks.
method Replica exchange Langevin Monte Carlo, control variates method, population-chain replica exchange, scalable dynamic importance sampling.
result Control variates method reduces variance and accelerates convergence in non-convex Bayesian learning.
New minibatching strategy reduces stochastic gradient bias in optimisation.
problem Reducing bias in stochastic gradient descent.
method Symmetric Minibatching Strategy combined with momentum.
result Reduced stochastic gradient bias from to .
This work analyzes Batch Normalization through convex optimization, providing insights and improved training methods.
problem Understanding and improving the effectiveness of Batch Normalization in deep neural networks.
method Introducing convex duality to model weight-decay regularized ReLU networks with BN, and designing an explicit regularization approach.
result Gradient Descent provides an algorithmic bias effect on BN networks, which can be explicitly encoded into the convex objective.
Sharp bounds established for Federated Averaging (FedAvg), improving convergence rates.
problem Undetermined convergence rate of Federated Averaging (FedAvg) in Federated Learning.
method Developed novel iterate bias concept and proved sharp bounds on it, leading to improved convergence results.
result Lower bounds for FedAvg match existing upper bounds, showing no improvable capacity.
Debiased Wasserstein barycenters improve on entropy regularization in OT.
problem Entropy regularization in OT introduces bias, leading to blurred barycenters.
method Propose debiased Wasserstein barycenters using Sinkhorn iterations.
result Debiased barycenters preserve fast Sinkhorn-like iterations without entropy smoothing bias.
Improved sampling efficiency with Random Reshuffling for Langevin dynamics.
problem Sampling efficiency in stochastic gradient algorithms.
method Random Reshuffling for Stochastic Gradient Langevin Dynamics (SGLD).
result Random Reshuffling leads to improved performance in sampling.
Unified framework for stability and generalization of Push-Sum in decentralized learning over directed graphs.
problem Understanding stability and generalization of Push-Sum in decentralized learning over directed networks.
method Developed a unified uniform-stability framework for SGP algorithm, incorporating imbalance-aware consistency bounds.
result Established finite-iteration stability and optimization guarantees for convex and non-convex objectives.
We show that the herding procedure of Welling (2009) takes exactly the form of a standard convex optimization algorithm--namely a conditional gradient algorithm minimizing a quadratic moment discrepancy. This link enables us to invoke convergence results from convex optimization and to consider faster alternatives for …
Paper proves convergence for private FL on non-Lipschitz convex objectives using normalization instead of clipping.
problem Lack of convergence results for differentially private federated learning with non-Lipschitz objectives.
method Developed a convergence result for private FL on smooth convex objectives without assuming Lipschitzness, using normalization instead of clipping.
result Normalization-based private FL algorithm converges better than clipping-based counterpart on smooth convex functions.
This work explains why online imitation learning improves faster than theory predicts.
problem Online imitation learning's empirical policy improvement speed exceeds theoretical predictions.
method The authors analyze online imitation learning with a convex, smooth, and non-negative loss function, proving policy improvement in expectation and high probability.
result Adopting a sufficiently expressive policy class in online IL increases both policy improvement speed and performance bias.
ASGD outperforms SGD in overparameterized linear regression, especially in subspaces of small eigenvalues.
problem Generalization of ASGD for overparameterized linear regression.
method Established instance-dependent excess risk bound for ASGD in each eigen-subspace of the data covariance matrix.
result ASGD outperforms SGD in subspaces of small eigenvalues, exhibiting faster decay of bias error.
Label noise SGD converges to a simple model with a single linear feature.
problem Understanding the simplicity bias in neural network training.
method Analyzing the convergence of label noise SGD on two-layer neural networks.
result Label noise SGD converges to a model with a single linear feature.
Develop a comprehensive theory for regularized M-estimation in reproducing kernel Hilbert spaces.
problem Regularized M-estimation in reproducing kernel Hilbert spaces
method Existence and measurability of the estimator, sharp rates of convergence
result New rates for tensor product Sobolev spaces
Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approachcs.LG
Develops a new method to improve performance in multi-objective learning problems.
problem Gradient bias in multi-objective learning leading to degraded performance.
method Stochastic Multi-objective gradient Correction (MoCo) method that guarantees convergence without increasing batch size.
result Demonstrates effectiveness of MoCo method in simulations on multi-task learning.
Proposes -balancing for more balanced expert utilization in MoE models.
problem Balanced expert utilization in MoE models to avoid bias.
method Directly targets population-level balance by minimizing a convex potential function.
result Consistently outperforms prior methods in stability and effectiveness.
We develop a family of accelerated stochastic algorithms that minimize sums of convex functions. Our algorithms improve upon the fastest running time for empirical risk minimization (ERM), and in particular linear least-squares regression, across a wide range of problem settings. To achieve this, we establish a framewo…
Tensor completion and robust principal component analysis have been widely used in machine learning while the key problem relies on the minimization of a tensor rank that is very challenging. A common way to tackle this difficulty is to approximate the tensor rank with the norm of singular values based on its …
Recent work has shown how to embed differentiable optimization problems (that is, problems whose solutions can be backpropagated through) as layers within deep learning architectures. This method provides a useful inductive bias for certain problems, but existing software for differentiable optimization layers is rigid…