Research
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

1223 · Jun 201319922001200920172026
48 results for ICML

The paper introduces explainable kk-means with axis-parallel hyperplanes for dd-dimensional data.

problem Creating explainable clustering with axis-parallel hyperplanes for complex data.
method An efficient algorithm that finds an explainable clustering with a near-optimal cost function.
result The algorithm achieves a near-optimal kk-means cost of k12/dpolylog(k)k^{1 - 2/d}\,\mathrm{polylog}(k) for dd-dimensional data.

Reduced sample complexity for group-invariant distributions.

problem Improving sample complexity for estimating divergences of group-invariant distributions.
method Quantified reduction in sample complexity for Wasserstein-1 metric and Lipschitz-regularized α-divergences under finite and infinite groups.
result Sample complexity reduction proportional to group size for finite groups, and convergence rate depends on intrinsic dimension for infinite groups.

We consider the problem of classification using similarity/distance functions over data. Specifically, we propose a framework for defining the goodness of a (dis)similarity function with respect to a given learning task and propose algorithms that have guaranteed generalization properties when working with such good fu…

2011-12-22abs ↗pdf ↗

We consider the problem of learning a low-rank matrix, constrained to lie in a linear subspace, and introduce a novel factorization for modeling such matrices. A salient feature of the proposed factorization scheme is it decouples the low-rank and the structural constraints onto separate factors. We formulate the optim…

2017-04-24abs ↗pdf ↗

This paper develops coding techniques to reduce the running time of distributed learning tasks. It characterizes the fundamental tradeoff to compute gradients (and more generally vector summations) in terms of three parameters: computation load, straggler tolerance and communication cost. It further gives an explicit c…

2018-02-09abs ↗pdf ↗

Survey on random features for kernel approximation, focusing on algorithms, theory, and practical applications.

problem Efficiently approximating kernel methods for large-scale problems.
method Random features techniques to speed up kernel methods.
result Need for a high number of random features for good approximation quality.

A new framework for selecting base classes in multi-class classification boosts accuracy.

problem Selecting the base class in multi-class classification to improve accuracy.
method Introduces a unified framework with parameters (s,g,w)(s,g,w) to search for the base class at each boosting iteration, improving computational efficiency.
result Our framework can achieve better test accuracy than the exhaustive search strategy, providing a robust and reliable scheme.

Recently, fully-connected and convolutional neural networks have been trained to achieve state-of-the-art performance on a wide variety of tasks such as speech recognition, image classification, natural language processing, and bioinformatics. For classification tasks, most of these "deep learning" models employ the so…

2013-06-02abs ↗pdf ↗

Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and time-consuming human-powered processes such as model design, algorithm development, and hyperparameter tuning. In this paper, we verify that au…

2018-06-11abs ↗pdf ↗

Contrastive learning performance doesn't degrade with more negative samples.

problem Theoretical and empirical evidence of negative samples hurting performance in contrastive learning.
method Simple theoretical setting and empirical support on CIFAR-10 and CIFAR-100 datasets.
result Contrastive learning performance does not degrade with the number of negative samples.

New method removes specific training data influence from neural networks.

problem Removing specific training data influence from neural networks for privacy and regulatory reasons.
method Noisy fine-tuning on retain data to ensure provable unlearning guarantees without restrictive assumptions.
result Achieves formal unlearning guarantees and performs effectively in practice.

Improved bilevel model solves complex machine learning problems faster and more accurately.

problem Complex hierarchical machine learning problems with inner and outer problem correlation.
method Proposed an improved bilevel model with theoretical guarantees and empirical validation.
result Empirical results show our model outperforms current bilevel models significantly.

Differentially private random block coordinate descent improves utility in machine learning.

problem Lack of privacy in classical CD methods when handling sensitive information.
method Proposes a differentially private random block coordinate descent method using sketch matrices and importance sampling.
result Demonstrates improved convergence rates and utility guarantees compared to non-private methods.

Study minimax regret in bilateral trade with heavy-tailed valuations.

problem Minimizing regret in bilateral trade with infinite variance valuations.
method Extended self-bounding property, truncated-mean estimation, epoch-based algorithm.
result Achieves regret bound of O(T12β(p1)/(βp+d(p1)))O(T^{1-2β(p-1)/(βp + d(p-1))}) under specific conditions.

New bounds show complex neural networks need many queries to learn.

problem Learning non-polynomial activation functions with Gaussian marginals.
method Gradient boosting procedure to amplify lower bounds on SQ dimension of neural networks.
result Statistical-query lower bounds for ReLU regression with 2ncε2^{n^c} ε queries.

Critiques binary classification evaluation methods, advocating for proper scoring rules.

problem The dominance of top-K metrics and fixed-threshold evaluations in machine learning.
method Introduces a decision-theoretic framework mapping evaluation metrics to their use cases, and implements a clipped Brier score variant.
result Demonstrates the clinical utility of proper scoring rules through a Python package, exttt{briertools}.

Group equivariant neural networks simplify complex tasks with group representation theory.

problem Challenging tasks requiring input transformations like rotations.
method Group representation theory, non-commutative harmonic analysis, differential geometry.
result A neural network is group equivariant if and only if it has a convolutional structure.

Improved mistake bound for group linear separable cases in online multiclass linear classification.

problem Improving mistake bounds for online multiclass linear classification under group linear separable conditions.
method Refined group weak linear separability condition and rational kernel approach.
result Achieved a mistake bound of K2ildeO(1/γlogL))K\cdot 2^{ ilde{O}(\sqrt{1/γ}\log L)}) under group weak linear separable condition.

New algorithms learn graphons in GMFGs without knowing them.

problem Learning graphons in Graphon Mean-Field Games with unknown graphons.
method Proximal Policy Optimization for GMFG (GMFG-PPO) and kernel embedding methods for estimating graphons.
result The proposed algorithms reduce exploitability when learning unknown graphons.

Feature hashing and other random projection schemes are commonly used to reduce the dimensionality of feature vectors. The goal is to efficiently project a high-dimensional feature vector living in Rn\mathbb{R}^n into a much lower-dimensional space Rm\mathbb{R}^m, while approximately preserving Euclidean norm. These sc…

2019-03-08abs ↗pdf ↗

The paper analyzes covariate shift in nonparametric regression with Markovian data.

problem Covariate shift in regression problems with Markovian data.
method Extension of nonparametric convergence rates to Markovian dependence structures, using Hölder smoothness assumptions and similarity measures.
result Precise convergence rates for Nadaraya-Watson kernel estimators under specific Markovian conditions.

Improved learning bounds for corrupted data using thresholded gradient descent.

problem Learning from corrupted data with adversarial noise.
method Thresholded gradient descent for sigmoidal, leaky-ReLU, and ReLU activations.
result Improved approximation bounds for various activation functions.