Algorithm optimizes ε-SVR with MAPE loss and sample-dependent constraints.
problem Optimizing ε-SVR with MAPE loss and sample-dependent constraints.
method Sequential Minimal Optimization (SMO) for ε-SVR with MAPE loss and sample-dependent box constraints.
result Algorithm achieves lowest median runtime on every tested configuration.
New method for private learning with fairness constraints.
problem Rate-constrained optimization under differential privacy.
method RaCO-DP, a DP variant of SGDA solving Lagrangian formulation.
result Empirical results show RaCO-DP outperforms existing methods.
In this paper, we consider the problem of column subset selection. We present a novel analysis of the spectral norm reconstruction for a simple randomized algorithm and establish a new bound that depends explicitly on the sampling probabilities. The sampling dependent error bound (i) allows us to better understand the …
New inequalities for unbounded functions improve denoising score matching.
problem Statistical error bounds for denoising score matching with unbounded objective functions.
method Derive new concentration inequalities using McDiarmid's inequality and Rademacher complexity bounds.
result Improved statistical error bounds for denoising score matching.
DMLE improves active learning by correcting MLE for sample dependencies.
problem Dependencies among samples in active learning affect model parameter estimation.
method Dependency-aware Maximum Likelihood Estimation (DMLE).
result DMLE achieves superior performance across multiple benchmark datasets.
We show a connection between the Fourier spectrum of Boolean functions and the REINFORCE gradient estimator for binary latent variable models. We show that REINFORCE estimates (up to a factor) the degree-1 Fourier coefficients of a Boolean function. Using this connection we offer a new perspective on variance reduction…
Recently, an extension of independent component analysis (ICA) from one to multiple datasets, termed independent vector analysis (IVA), has been the subject of significant research interest. IVA has also been shown to be a generalization of Hotelling's canonical correlation analysis. In this paper, we provide the ident…
Transformers capture combinatorial tasks with bounded error and logarithmic sample dependence.
problem Capturing complex combinatorial tasks with bounded error and sample efficiency.
method Formal definition of algorithmic capture, empirical analysis of infinite-width transformers, upper bounds on computational complexity.
result Transformers exhibit an inductive bias favoring simpler algorithmic procedures over higher complexity ones.
Proposes a new method to measure classifier robustness.
problem Measuring robustness of classifiers is crucial but challenging.
method Weighting sample importance based on difficulty and using logistic regression as a theoretical case study.
result The proposed score is independent of sample choice and measures robustness effectively.
New method improves active statistical inference by reducing noise.
problem Inaccurate uncertainty estimates in active sampling lead to noisy results.
method Robust sampling strategies that interpolate between uniform and active sampling based on uncertainty scores.
result The robust sampling ensures that the estimator is never worse than uniform sampling and usually outperforms active inference.
Probabilistic linear discriminant analysis (PLDA) is a method used for biometric problems like speaker or face recognition that models the variability of the samples using two latent variables, one that depends on the class of the sample and another one that is assumed independent across samples and models the within-c…
Regularization is a well recognized powerful strategy to improve the performance of a learning machine and lq regularization schemes with 0<q<∞ are central in use. It is known that different q leads to different properties of the deduced estimators, say, l2 regularization leads to smooth estimators while…
New method for differentially private optimization with general Lipschitz conditions.
problem Differentially private optimization under general Lipschitz conditions.
method Generalized Lipschitz condition for per-sample gradients, tuning clip norm based on minimum per-sample Lipschitz constant.
result Efficacy of the recommended clip norm tuning method verified on 8 datasets.
Linear time algorithm for random walk kernels on sparse graphs.
problem Efficient computation of general random walk kernels for large graphs.
method Sample dependent random walks to compute graph embeddings without direct graph product.
result Up to 27x faster and scalable to 128x larger graphs than previous methods.
We make a minimal, but very effective alteration to the VAE model. This is about a drop-in replacement for the (sample-dependent) approximate posterior to change it from the standard white Gaussian with diagonal covariance to the first-order autoregressive Gaussian. We argue that this is a more reasonable choice to ado…
Paper improves generalization bounds for noisy stochastic algorithms.
problem Improving generalization bounds for noisy stochastic algorithms.
method Introduces Exponential Family Langevin Dynamics (EFLD) and establishes data-dependent expected stability based generalization bounds.
result Sharp generalization bounds with O(1/n) sample dependence and gradient discrepancy.
New method for cross-validation in high-dimensional data with dependent or heavy-tailed covariates.
problem Inconsistent cross-validation in high-dimensional settings with dependent or heavy-tailed covariates.
method ROTI-GCV framework for cross-validation under proportional asymptotics regime.
result Demonstrated accuracy of ROTI-GCV in synthetic and semi-synthetic settings.
A grand challenge in representation learning is to learn the different explanatory factors of variation behind the high dimen- sional data. Encoder models are often determined to optimize performance on training data when the real objective is to generalize well to unseen data. Although there is enough numerical eviden…
Generative models enhance weak supervision for better image classification.
problem Lack of labeled data in supervised learning.
method Fusion of generative adversarial networks and weak supervision.
result Model improves multiclass image classification performance.
New method assesses individual training points' privacy risk without retraining.
problem Privacy vulnerability of individual training points in membership inference attacks.
method Derives a closed-form decomposition of individual black-box MIA vulnerability, extending to deep networks.
result Proposes a surrogate score operating on last-layer representations that requires only a single trained model.
New algorithm reduces feature count and accelerates error convergence.
problem Exponential error convergence in data classification with optimized random features.
method Optimized random features accelerated by quantum machine learning.
result Achieves exponential error convergence under low-noise condition.
Dropout has been witnessed with great success in training deep neural networks by independently zeroing out the outputs of neurons at random. It has also received a surge of interest for shallow learning, e.g., logistic regression. However, the independent sampling for dropout could be suboptimal for the sake of conver…
lq-regularization has been demonstrated to be an attractive technique in machine learning and statistical modeling. It attempts to improve the generalization (prediction) capability of a machine (model) through appropriately shrinking its coefficients. The shape of a lq estimator differs in varying choices of the…
New method estimates covariance in deep heteroscedastic regression without labels.
problem Estimating covariance in deep heteroscedastic models is challenging due to sample-dependent covariance and lack of ground truth.
method Proposes a self-supervised approach using KL Divergence and 2-Wasserstein distance for covariance estimation and a neighborhood-based heuristic for pseudo labels.
result Demonstrates effective pseudo labels and a computationally cheaper yet accurate deep heteroscedastic regression.
Unified toolkit for comparing neural representations using SRTD and NTS.
problem Heuristic asymmetry and unbounded scores in existing divergences.
method Developed SRTD and NTS to address these issues.
result Unified, robust, and scale-invariant metric for comparing neural representations.
Copula Discrepancy benchmarks sample dependence structure against known families.
problem Benchmarking sample dependence structure against known families.
method Copula Discrepancy (CD) statistic comparing target Kendall's tau with fitted parameter.
result CD reliably separates on-target and off-target copulas.
Proposes a method to combine datasets with missing values using Gaussian process latent variables.
problem Combining datasets with missing values under non-Missing at Random (NMAR) missingness.
method Gaussian process latent variable model for non-MAR missing data.
result Valid estimates are obtained using the proposed method, while existing methods provide severely biased estimates.
This paper identifies drift Lipschitz budget K as key to diffusion policy expressivity and statistical trade-offs.
problem Understanding and maximizing the expressivity of diffusion policies while managing statistical limitations.
method Identifying drift Lipschitz budget K as central, quantifying expressivity and statistical behavior, proving lower bounds, and providing practical implementation guidelines.
result Balancing expressivity and statistical complexity yields a finite-sample performance gap, with rates depending on sample size and drift type.
A new algorithm tackles submodular bandit problems with multiple constraints.
problem Addressing diversified retrieval and online learning with budget constraints.
method Non-greedy algorithm focusing on upper-confidence bounds.
result High-probability upper bound of an approximation regret matching fast offline algorithm's ratio.
This work proposes an online learning approach to tighten constraints in stochastic control problems.
problem Solving chance-constrained stochastic optimal control problems is computationally challenging.
method Reformulate chance constraints as a binary regression problem and use a GP model to learn constraint-tightening parameters online.
result The approach tightens constraints more effectively, leading to lower costs in numerical experiments.
We study constrained clustering, where constraints guide the clustering process. In existing works, two categories of constraints have been widely explored, namely pairwise and cardinality constraints. Pairwise constraints enforce the cluster labels of two instances to be the same (must-link constraints) or different (…
Simplifies neural network constraints with computationally efficient method.
problem Implementing hard output constraints in neural networks.
method Additional neural network layer for output constraints.
result Computational simplicity with complexity O(n*m) for linear constraints.
Reduces Lie (bi-)algebroids and Dirac manifolds using constraint vector bundles.
problem Reduction of Lie (bi-)algebroids and Dirac manifolds.
method Introduces constraint manifolds and constraint vector bundles; proves constraint Serre-Swan theorem; introduces Cartan calculus for constraint forms and multivector fields; shows compatibility with reduction.
result Reduction procedure for Lie (bi-)algebroids and Dirac manifolds.
Optimistic algorithm reduces regret and constraint violations in online convex optimization with adversarial constraints.
problem Online convex optimization with adversarial constraints.
method Improved algorithm using accurate predictions of loss and constraint functions.
result Improved bounds on regret and cumulative constraint violations.
Holistic GLMs add constraints for better model quality.
problem Improving classical linear regression models.
method Sparsity-inducing, sign-coherence, and linear constraints.
result Holistic GLMs reliably solve GLMs for various responses.
This paper resolves BIHT convergence, showing normalization is not necessary in noiseless settings but crucial for robustness.
problem Analyzing convergence and robustness of BIHT for 1-bit compressed sensing.
method Characterizes BIHT convergence and robustness, proving necessity of normalization for robustness under sign corruptions.
result Per-iteration normalization is not necessary for optimal recovery in noiseless settings but is crucial for robustness under sign corruptions.
A new ML method teaches constraints directly to models.
problem Addressing safety and fairness in AI systems.
method Directly teaching constraint satisfaction to ML models using a constraint solver.
result Empirically, our approach performs well on fairness and synthetic constraints.
Paper tackles constrained bandit problems with a new learning framework.
problem Optimizing a black-box reward function subject to a black-box constraint function over a continuous space.
method Rectified Pessimistic-Optimistic Learning (RPOL) framework, incorporating optimistic and pessimistic GP bandit learning.
result RPOL achieves sublinear regret and minimal cumulative constraint violation.
In the present paper, the minimal investment risk for a portfolio optimization problem with imposed budget and investment concentration constraints is considered using replica analysis. Since the minimal investment risk is influenced by the investment concentration constraint (as well as the budget constraint), it is i…
Survey of Gaussian process constraints for modeling expensive data.
problem Modeling expensive data with physical constraints.
method Overview of various Gaussian process constraints and their implementation.
result Discussion of computational challenges introduced by constraints.
This paper considers online convex optimization over a complicated constraint set, which typically consists of multiple functional constraints and a set constraint. The conventional online projection algorithm (Zinkevich, 2003) can be difficult to implement due to the potentially high computation complexity of the proj…
We provide a dynamic programming principle for stochastic optimal control problems with expectation constraints. A weak formulation, using test functions and a probabilistic relaxation of the constraint, avoids restrictions related to a measurable selection but still implies the Hamilton-Jacobi-Bellman equation in the …
Iterative method learns unknown constraints for MPC control.
problem Learning to satisfy unknown polyhedral state constraints in iterative MPC.
method Collects and improves estimates of unknown constraints using collected data, designs an MPC controller to satisfy the estimated constraints.
result Robust and probabilistic guarantees of constraint satisfaction as a function of task iterations.
We reformulate data-dependent constraints to ensure they are always met with high probability.
problem Ensuring fairness and stability in machine learning models with data-dependent constraints.
method Calibrated reformulation of constraints to guarantee satisfaction with a specified probability.
result Our method guarantees that fairness constraints are met at test time with high probability.
New algorithm reduces regret and constraint violation in online convex optimization with complex constraints.
problem Online convex optimization with multiple functional constraints and a simple constraint set.
method Instance-dependent bound using online primal-dual mirror-prox algorithm in general normed spaces.
result Achieves an O(√V*(T)) regret and O(1) constraint violation, improving over previous works.
Algorithm ensures privacy while strictly adhering to constraints.
problem Differential privacy with linear constraints that must be strictly followed.
method Developed an algorithm that releases a nearly-optimal solution satisfying constraints with probability 1.
result Achieved nearly optimal performance while preserving privacy and strictly adhering to constraints.
Proposes NUV priors for half-space and box constraints.
problem Adding constraints to linear Gaussian models without computational cost.
method Introduces NUV representations for half-space and box constraints.
result Adds constraints to linear Gaussian models without affecting computational tractability.
Meta-gradient D4PG optimizes performance and constraint adherence in RL.
problem Balancing performance and adherence to complex constraints in RL.
method Uses meta-gradients to find a balance between expected return and minimizing constraint violations.
result Meta-gradient D4PG consistently outperforms baselines across MuJoCo domains.