arXiv research

Paper develops an online learning algorithm for functional data models.

Study derives error decay rates for kernel classification under source and capacity conditions.

The study analyzes prediction errors in systems with memory kernels, providing bounds and stability results.

Proposes a method to improve deep active learning for NER tasks.

Analyzes dynamics of quantum neural networks, predicting exponential decay of training error.

New model predicts links in community-based networks robustly.

Paper uses AI to predict medications from medical codes, improving accuracy in healthcare.

The study examines Kernel Ridge Regression error rates across noiseless and noisy conditions.

This paper extends neural collapse to regression problems, revealing key features and structures.

Theoretical justification for deep networks' performance with regularization techniques.

We analyze two communication-efficient algorithms for distributed statistical optimization on large-scale data sets. The first algorithm is a standard averaging method that distributes the $N$ data samples evenly to $\nummac$ machines, performs separate minimization on each subset, and then averages the estimates. We p…

Improved online prediction with guaranteed coverage.

The paper predicts and explains the decay of stock anomaly performance over time.

We informally call a stochastic process learnable if it admits a generalization error approaching zero in probability for any concept class with finite VC-dimension (IID processes are the simplest example). A mixture of learnable processes need not be learnable itself, and certainly its generalization error need not de…

New approach uses Gaussian processes to learn and track complex systems with guaranteed accuracy.

Study reveals phase transition in neural networks near interpolation.

Adam's generalization performance is improved by batch size and weight decay in neural networks.

We found that factors decay over time, with momentum fitting best.

We find a deterministic equivalent for random feature regression's test error, independent of feature map dimension.

Active data collection improves convergence rates in operator learning.

This paper deals with two related problems, namely distance-preserving binary embeddings and quantization for compressed sensing . First, we propose fast methods to replace points from a subset $\mathcal{X} \subset \mathbb{R}^n$, associated with the Euclidean metric, with points in the cube $\{\pm 1\}^m$ and we associa…

Under what conditions is an edge present in a social network at time t likely to decay or persist by some future time t + Delta(t)? Previous research addressing this issue suggests that the network range of the people involved in the edge, the extent to which the edge is embedded in a surrounding structure, and the age…

A new distillation method transfers channel information from teacher to student.

Efficiently compress pretrained models using RSI for improved predictive accuracy.

Estimates kernel eigenvalues for compositional dot-product kernels.

Interpolating models can have heavy-tailed risk, leading to rare but severe errors.

In this paper we consider the cluster estimation problem under the Stochastic Block Model. We show that the semidefinite programming (SDP) formulation for this problem achieves an error rate that decays exponentially in the signal-to-noise ratio. The error bound implies weak recovery in the sparse graph regime with bou…

Boosting framework for vector-valued prediction with geometric stability.

Machine learning systems increasingly depend on pipelines of multiple algorithms to provide high quality and well structured predictions. This paper argues interaction effects between clustering and prediction (e.g. classification, regression) algorithms can cause subtle adverse behaviors during cross-validation that m…

The paper provides convergence guarantees for multicalibration gradient boosting.

Generalizes neural tangent kernel analysis for two-layer networks with noise and regularization.

Study on infinitely-wide CNNs and their adaptability to function spatial scales.

Study efficient neural operator learning using variation spaces.

LPF provides formal guarantees for aggregating multi-evidence in probabilistic tasks.

New bounds for KRR condition number reveal overfitting phenomena.

The goal of predictive sparse coding is to learn a representation of examples as sparse linear combinations of elements from a dictionary, such that a learned hypothesis linear in the new representation performs well on a predictive task. Predictive sparse coding algorithms recently have demonstrated impressive perform…

New research shows fixed-budget best-arm identification cannot match static oracle performance.

Optimal multistage method solves noisy minimax problems.

The paper improves transformer generalization bounds using rank-dependent covering number bounds.

We develop a novel approximate simulation algorithm for the joint law of the position, the running supremum and the time of the supremum of a general Lévy process at an arbitrary finite time. We identify the law of the error in simple terms. We prove that the error decays geometrically in $L^p$ (for any $p\geq 1$) as a…

Model proposes neural network for continuous time dynamics with inductive biases.

Paper proves Gromov's conjecture on manifolds with certain group properties.

Neural processes approximate Gaussian process inference, revealing three key costs.

This study examines how large language models learn in-context and provides insights into their performance and architecture.

SGD and weight decay encourage neural networks to learn low-rank weight matrices.

SA-PEF improves federated learning efficiency by correcting gradient mismatches.

Study proposes GRU-D networks for missing value handling in road surface friction prediction.

As the success of deep learning reaches more grounds, one would like to also envision the potential limits of deep learning. This paper gives a first set of results proving that certain deep learning algorithms fail at learning certain efficiently learnable functions. The results put forward a notion of cross-predictab…