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.
New neural methods for stable control with provable guarantees.
Math proves deep learning unstable, despite stable neural networks existing.
Stable neural flows ensure robustness and efficiency in deep learning.
Lipschitz constraints under L2 norm on deep neural networks are useful for provable adversarial robustness bounds, stable training, and Wasserstein distance estimation. While heuristic approaches such as the gradient penalty have seen much practical success, it is challenging to achieve similar practical performance wh…
No feature ranking can be faithful, stable, and complete when features are collinear.
We provide initial seedings to the Quick Shift clustering algorithm, which approximate the locally high-density regions of the data. Such seedings act as more stable and expressive cluster-cores than the singleton modes found by Quick Shift. We establish statistical consistency guarantees for this modification. We then…
New stable HOIF estimators for statistical functionals.
New algorithm learns stable LDSs with lower error and better control performance.
New SVM margin bound improves generalization in machine learning.
Studied how SGD's stability regularization affects generalization in neural networks.
While deep reinforcement learning has successfully solved many challenging control tasks, its real-world applicability has been limited by the inability to ensure the safety of learned policies. We propose an approach to verifiable reinforcement learning by training decision tree policies, which can represent complex p…
We develop efficient algorithms to estimate the stability of Ordinary Least Squares regression results.
Paper introduces stable vectorization for multiparameter PH using signed barcodes.
New method identifies stable latent variables across different domains using weak distributional invariances.
We establish that first-order methods avoid saddle points for almost all initializations. Our results apply to a wide variety of first-order methods, including gradient descent, block coordinate descent, mirror descent and variants thereof. The connecting thread is that such algorithms can be studied from a dynamical s…
Paper resolves bias in ALFT training using generalized alignment games.
Deep networks realize complex mappings that are often understood by their locally linear behavior at or around points of interest. For example, we use the derivative of the mapping with respect to its inputs for sensitivity analysis, or to explain (obtain coordinate relevance for) a prediction. One key challenge is tha…
Approximate algorithms for structured prediction problems---such as LP relaxations and the popular alpha-expansion algorithm (Boykov et al. 2001)---typically far exceed their theoretical performance guarantees on real-world instances. These algorithms often find solutions that are very close to optimal. The goal of thi…
This paper describes a suite of algorithms for constructing low-rank approximations of an input matrix from a random linear image of the matrix, called a sketch. These methods can preserve structural properties of the input matrix, such as positive-semidefiniteness, and they can produce approximations with a user-speci…
Persistence diagrams (PDs) play a key role in topological data analysis (TDA), in which they are routinely used to describe topological properties of complicated shapes. PDs enjoy strong stability properties and have proven their utility in various learning contexts. They do not, however, live in a space naturally endo…
New method aligns diffusion models for inference-time properties without retraining.
Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations. Most of these methods are based on minimizing an upper bound on the worst-case loss over all possible adversarial perturbations. While these techniques show promise, they often res…
We deconstruct the performance of GANs into three components: 1. Formulation: we propose a perturbation view of the population target of GANs. Building on this interpretation, we show that GANs can be viewed as a generalization of the robust statistics framework, and propose a novel GAN architecture, termed as Cascade …
Convolutional neural networks (CNNs) often perform well, but their stability is poorly understood. To address this problem, we consider the simple prototypical problem of signal denoising, where classical approaches such as nonlinear diffusion, wavelet-based methods and regularisation offer provable stability guarantee…
Sparse representations using learned dictionaries are being increasingly used with success in several data processing and machine learning applications. The availability of abundant training data necessitates the development of efficient, robust and provably good dictionary learning algorithms. Algorithmic stability an…
Standard stochastic optimization methods are brittle, sensitive to stepsize choices and other algorithmic parameters, and they exhibit instability outside of well-behaved families of objectives. To address these challenges, we investigate models for stochastic minimization and learning problems that exhibit better robu…
New neural stack and Turing Machine architectures prove stability and computational power.
Stabilized neural differential equations enforce constraints on dynamical systems.
WSqD extends learning rate schedules for large model training without fixed horizons.
Algorithm recovers multiple low-rank matrices from unlabeled data.
Framework combines adversarial training and provable robustness for neural networks.
This paper reviews information theory in open-world machine learning.
New algorithm robust to outliers in Bayesian Optimization.
DSPM models control noise volatility, improving financial data analysis.
The paper uses persistent homology to estimate recurrence times in multi-variate time series.
New measures quantify diversity of latent representations using metric space magnitude.
We propose a novel ranking model that combines the Bradley-Terry-Luce probability model with a nonnegative matrix factorization framework to model and uncover the presence of latent variables that influence the performance of top tennis players. We derive an efficient, provably convergent, and numerically stable majori…
Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to -norm adversarial perturbations. In this paper, we employ adversarial training to improve the performance of randomized smoothing. We design an adap…
Hyper addresses the hyperparameter tuning challenge in RL, improving exploration efficiency and robustness.
Topic models provide a useful method for dimensionality reduction and exploratory data analysis in large text corpora. Most approaches to topic model inference have been based on a maximum likelihood objective. Efficient algorithms exist that approximate this objective, but they have no provable guarantees. Recently, a…
PerfGD solves model-induced data shifts by finding optimal points.
In recent years several adversarial attacks and defenses have been proposed. Often seemingly robust models turn out to be non-robust when more sophisticated attacks are used. One way out of this dilemma are provable robustness guarantees. While provably robust models for specific -perturbation models have been dev…
New method uses deep learning to solve inverse problems with provable guarantees.
The idea of Innovation Search was proposed as a data clustering method in which the directions of innovation were utilized to compute the adjacency matrix and it was shown that Innovation Pursuit can notably outperform the self representation based subspace clustering methods. In this paper, we present a new discovery …
PARADE generates provably robust adversarial examples for deep networks.
Framework for fair classification with noisy protected attributes and provable guarantees.
New theory shows large learning rates prevent overfitting in neural networks.
Persistence diagrams, the most common descriptors of Topological Data Analysis, encode topological properties of data and have already proved pivotal in many different applications of data science. However, since the (metric) space of persistence diagrams is not Hilbert, they end up being difficult inputs for most Mach…