New decision-theoretic calibration error metric improves prediction reliability.
problem Improving the reliability of predictions for decision-making.
method Proposed Calibration Decision Loss (CDL) and an efficient algorithm to achieve near-optimal CDL.
result Near-optimal CDL guarantees vanishing payoff loss from miscalibration.
The paper provides theoretical guarantees for optimized sampling in compressed sensing, showing error vanishes with more measurements.
problem Theoretical and practical improvements in compressed sensing with optimized sampling schemes.
method Theoretical analysis and empirical experiments with optimized sampling schemes for subsampled unitary matrices.
result The error caused by measurement noise vanishes with an increasing number of measurements for optimized sampling schemes, assuming Gaussian noise.
Paper establishes bounds for RNN-TPPs, showing four-layer networks can achieve vanishing errors.
problem Understanding theoretical limits of RNN-TPPs.
method Characterized RNN complexity, constructed neural approximations, applied truncation technique.
result Four-layer RNN-TPPs can achieve vanishing generalization errors.
Approximate vanishing ideal is a concept from computer algebra that studies the algebraic varieties behind perturbed data points. To capture the nonlinear structure of perturbed points, the introduction of approximation to exact vanishing ideals plays a critical role. However, such an approximation also gives rise to a…
We study utility indifference prices and optimal purchasing quantities for a contingent claim, in an incomplete semi-martingale market, in the presence of vanishing hedging errors and/or risk aversion. Assuming that the average indifference price converges to a well defined limit, we prove that optimally taken position…
New approach uses Gaussian processes to learn and track complex systems with guaranteed accuracy.
problem Inaccurate first principle models for complex systems due to data complexity.
method Bayesian prediction error bound for Gaussian process regression, derived from kernel-based data density.
result Achieves vanishing tracking error with increasing data density, providing time-varying accuracy guarantees.
The main aim of this paper is to provide an analysis of gradient descent (GD) algorithms with gradient errors that do not necessarily vanish, asymptotically. In particular, sufficient conditions are presented for both stability (almost sure boundedness of the iterates) and convergence of GD with bounded, (possibly) non…
Background: Statistical mechanics results (Dauphin et al. (2014); Choromanska et al. (2015)) suggest that local minima with high error are exponentially rare in high dimensions. However, to prove low error guarantees for Multilayer Neural Networks (MNNs), previous works so far required either a heavily modified MNN mod…
We consider the problem of decentralized consensus optimization, where the sum of n smooth and strongly convex functions are minimized over n distributed agents that form a connected network. In particular, we consider the case that the communicated local decision variables among nodes are quantized in order to all…
Develops a method to estimate rare-event probabilities under distributional uncertainty.
problem Distributional uncertainty limits the effectiveness of rare-event simulation techniques.
method Wasserstein distributionally robust rare-event simulation (DRIS) framework.
result DRIS achieves vanishing relative error in estimating rare-event probabilities.
The problem of forecasting conditional probabilities of the next event given the past is considered in a general probabilistic setting. Given an arbitrary (large, uncountable) set C of predictors, we would like to construct a single predictor that performs asymptotically as well as the best predictor in C, on any data.…
New characterization limits sampling with inexact scores.
problem Limiting sampling with inexact scores for unbiased results.
method Characterized types of inexact score oracle access.
result Weaker error assumptions rule out tractability of unbiased sampling.
Paper tackles identifying an odd arm in a multi-armed bandit with restless Markov processes and trembling hand.
problem Identifying an odd arm in a multi-armed bandit with restless Markov processes and trembling hand.
method Derive asymptotic lower bound on expected time to identify the odd arm, stitch together parameterised solutions to MDPs.
result First known asymptotic lower bound on expected time to identify the odd arm, with vanishing error probability.
Study on error probabilities of machine learning classification techniques using large deviations theory.
problem Performance analysis of machine learning binary classification techniques.
method Large deviations theory applied to Data-Driven Decision Function (D3F) for error probability analysis.
result Classification error probabilities vanish exponentially, with an asymptotic formula providing precise error rate estimates.
SS-GEN simulates rare events in heavy and light-tailed data.
problem Estimating probabilities of extreme events in multivariate data.
method Self-Similar Generative Estimation (SS-GEN) decomposes tail distribution into radial and angular components.
result SS-GEN generates representative extreme scenarios and estimates rare-event probabilities beyond observed data.
Proposes a new model for mixed membership in Gaussian mixture.
problem Limited to single component membership in Gaussian mixture models.
method Mixed membership sub-Gaussian model, spectral algorithm.
result Estimation error can be made arbitrarily small with high probability.
Study on L2-boosting behavior as learning rate approaches zero.
problem Understanding the asymptotic behavior of L2-boosting algorithms with vanishing learning rates.
method Analyzes L2-boosting for regression with linear base learners, proving a deterministic limit and characterizing it as a solution to a linear differential equation.
result Proves the existence of a unique solution to the limit problem and analyzes the training and test error.
Attention mechanism learns to focus on sparse tokens efficiently.
problem Detecting weak, rare, and sparsely located features in long sequences.
method Theoretical analysis and training of a single-layer attention classifier in a sparse-token classification model.
result A single-layer attention classifier can achieve vanishing test error with logarithmic signal strength growth, unlike linear classifiers requiring linear growth.
Gradient descent with biased rounding errors converges faster under certain conditions.
problem Stagnation or negative impact of rounding errors in neural network training with low precision.
method Analysis of gradient descent with stochastic fixed-point rounding errors under the Polyak-Lojasiewicz inequality.
result Biased rounding errors can improve convergence rates, especially when the Polyak-Lojasiewicz inequality holds.
Study the properties of SGD in non-vanishing learning rate regime.
problem Understanding the noise and fluctuation in SGD with finite learning rates.
method Derive exact solvable results for discrete-time SGD in quadratic loss functions.
result Fluctuation caused by discrete-time dynamics is larger than continuous-time theory predicts.
We consider a problem of learning kernels for use in SVM classification in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin classifier. Our results show that, under mild conditions on the family of kernels used for learning, solving several related tasks simultaneou…
We study high-dimensional asymptotic performance limits of binary supervised classification problems where the class conditional densities are Gaussian with unknown means and covariances and the number of signal dimensions scales faster than the number of labeled training samples. We show that the Bayes error, namely t…
Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells. However, the extra parameters associated with the memory cells mean an LSTM layer has four times as many parameters as an RNN with the…
Inexact subgradient methods work well for semialgebraic functions with additive errors.
problem Approximate gradients in machine learning and optimization.
method Inexact subgradient methods with persistent additive errors in semialgebraic functions.
result Iterates eventually fluctuate near the critical set with a proximity of O(ερ), where ε is the magnitude of subgradient evaluation errors. Study linear regression with missing or corrupted data, showing error bounds.
problem Linear regression under missing or corrupted data.
method Information-theoretic lower bounds and efficient algorithms.
result Error bounds match in missing and corruption settings.
Bayesian regression underestimates parameter uncertainties in noisy models.
problem Parameter uncertainties are underestimated in Bayesian regression for imperfect models.
method Analyzed and designed an ansatz to correct for misspecification in near-deterministic surrogate models.
result Posterior distributions must cover all training points to avoid divergent generalization error.
This paper considers the recovery of a low-rank matrix from an observed version that simultaneously contains both (a) erasures: most entries are not observed, and (b) errors: values at a constant fraction of (unknown) locations are arbitrarily corrupted. We provide a new unified performance guarantee on when the natura…
We generalize recent theoretical work on the minimal number of layers of narrow deep belief networks that can approximate any probability distribution on the states of their visible units arbitrarily well. We relax the setting of binary units (Sutskever and Hinton, 2008; Le Roux and Bengio, 2008, 2010; Montúfar and Ay,…
This paper analyzes the interpolation error of nonlinear Attention compared to linear regression.
problem Understanding the interpolation error of nonlinear Attention in high-dimensional settings.
method Derives explicit expressions for mean-squared interpolation error using signal-plus-noise model and random matrix theory.
result Nonlinear Attention generally incurs a larger interpolation error than linear regression, but this gap can be reversed with structured signals.
A framework selects GANs for specific applications efficiently.
problem Fragmented knowledge leads to trial-error selection of GANs.
method Comprehensive summary of GANs, comparison, and novel framework.
result Significant reduction in search space for GAN selection.
Infinitesimal gradient boosting is a new algorithm derived from gradient boosting.
problem Improving the efficiency and smoothness of gradient boosting.
method Introduced a new class of randomized regression trees and used a limit process in vanishing-learning-rate asymptotic.
result Convergence of the stochastic algorithm and characterization of the limiting procedure as a unique solution of a nonlinear ODE.
We show through case studies that it is easier to estimate the fundamental limits of data processing than to construct explicit algorithms to achieve those limits. Focusing on binary classification, data compression, and prediction under logarithmic loss, we show that in the finite space setting, when it is possible to…
We present a new PAC-Bayesian generalization bound. Standard bounds contain a $\sqrt{L_n \cdot \KL/n}$ complexity term which dominates unless Ln, the empirical error of the learning algorithm's randomized predictions, vanishes. We manage to replace Ln by a term which vanishes in many more situations, essentially …
DP-PCA improves privacy in PCA computations with optimal statistical error.
problem Differentially private principal component analysis with sub-linear sample complexity.
method Private minibatch gradient ascent with private mean estimation.
result Achieves optimal statistical error rates for sub-Gaussian data with n=ildeO(d) samples. Training of deep models for classification tasks is hindered by local minima problems and vanishing gradients, while unsupervised layer-wise pretraining does not exploit information from class labels. Here, we propose a new regularization technique, called diversifying regularization (DR), which applies a penalty on hi…
Conditional diffusion models can approximate target distributions well with Gaussian-mixture reverse kernels.
problem Approximating target distributions in conditional diffusion models.
method Using finite Gaussian mixtures with ReLU-network logits as reverse kernels, reducing the problem to static conditional density approximation.
result The resulting neural reverse-kernel class is dense in conditional KL divergence under exact terminal matching.
New algorithm reduces regret in noisy context bandits.
problem Online decision-making with noisy context predictions.
method Extends classical statistics measurement error model to online decision-making.
result Achieves sublinear regret guarantees under mild conditions.
Analyzes Saito vanishing theorem using L2 methods.
problem Proving the Saito vanishing theorem.
method Uses L2-methods to prove the theorem. result Analytic proof of the Saito vanishing theorem.
In regression settings where explanatory variables have very low correlations and there are relatively few effects, each of large magnitude, we expect the Lasso to find the important variables with few errors, if any. This paper shows that in a regime of linear sparsity---meaning that the fraction of variables with a n…
Diffusion models generate data with Gaussian Universality, matching linear model test errors.
problem Analyzing the performance of models trained on synthetic data generated by diffusion models.
method Investigates Gaussian Universality for data distributions generated via diffusion models, matching test errors of linear models trained on synthetic data to Gaussian Mixture models.
result The test error of a linear model trained on diffusion-generated data matches the test error of a linear model trained on Gaussian Mixture data with matching means and covariances per class.
The paper stabilizes PD term structures under forecast uncertainty using a Kalman filter with an anchored observation model.
problem Stable estimation of lifetime PDs under forecast uncertainty.
method Reformulated in state-space framework, introduced an anchored observation model.
result Asymptotic stochastic stability of error dynamics, leading to smoother projections.
Infinitesimal boosting converges to a deterministic process in large sample limit.
problem Characterizing the asymptotic behavior of infinitesimal gradient boosting in large sample sizes.
method Proving convergence to a deterministic process using large sample theory and differential equations.
result The test error decreases over time in the population limit.
Deep Convolutional Neural Networks (CNN) enforces supervised information only at the output layer, and hidden layers are trained by back propagating the prediction error from the output layer without explicit supervision. We propose a supervised feature learning approach, Label Consistent Neural Network, which enforces…
This paper analyzes the impact of loops on bilevel optimization efficiency.
problem The impact of loops on the efficiency of bilevel optimization algorithms.
method Unified convergence analysis and computational complexity characterization for AID-BiO and ITD-BiO with and without loops.
result Loops in bilevel optimization can improve overall efficiency but increase per-step complexity.
The paper uses non-abelian Hodge theory to generalize Kodaira vanishing theorems.
problem Generalizing Kodaira vanishing theorems for non-abelian settings.
method Non-abelian Hodge theory and Mixed Twistor D-modules.
result Generalized Kodaira vanishing theorems for various settings.
Study on a knot invariant's vanishing order.
problem Understanding the vanishing order of twisted Alexander polynomials.
method Defined and explored properties of the twisted Alexander vanishing order.
result Listed twisted Alexander vanishing groups of order less than 201.
Recurrent Neural Networks (RNNs) are rich models for the processing of sequential data. Recent work on advancing the state of the art has been focused on the optimization or modelling of RNNs, mostly motivated by adressing the problems of the vanishing and exploding gradients. The control of overfitting has seen consid…
Proves a vanishing property for symplectic manifold cohomology.
problem Generalizing complex geometry results to symplectic geometry.
method Based on Tseng and Zhou's vanishing property under symplectic flatness.
result Establishes necessity of symplectic flatness for certain results.