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.
Active learning method for ABC statistics selection reduces expert work and improves posterior estimates.
New algorithm reduces robust optimization scale for better constraint satisfaction.
We address the problem of tuning word embeddings for specific use cases and domains. We propose a new method that automatically combines multiple domain-specific embeddings, selected from a wide range of pre-trained domain-specific embeddings, to improve their combined expressive power. Our approach relies on two key c…
In this paper, we study randomized reduction methods, which reduce high-dimensional features into low-dimensional space by randomized methods (e.g., random projection, random hashing), for large-scale high-dimensional classification. Previous theoretical results on randomized reduction methods hinge on strong assumptio…
Paper proposes SOTL framework for improving transfer learning accuracy and efficiency.
GENIE balances domain-invariant feature learning and gradient alignment for improved DG performance.
A new algorithm reduces bias and variance in distributionally robust optimization.
Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not utilise the continuity of the occurring shifts. In particular, many robotics appl…
This work establishes uniform convergence of subdifferentials in stochastic optimization.
Anchor PCA improves robustness in multi-domain PCA.
AutoScale improves LLM pre-training by adjusting data mixtures at different scales.
Every holomorphic effective parabolic or reductive geometry on a domain over a Stein manifold extends uniquely to the envelope of holomorphy of the domain. This result completes the open problems of my earlier paper on extension of holomorphic geometric structures on complex manifolds. We use this result to classify th…
Laplacian mixture models identify overlapping regions of influence in unlabeled graph and network data in a scalable and computationally efficient way, yielding useful low-dimensional representations. By combining Laplacian eigenspace and finite mixture modeling methods, they provide probabilistic or fuzzy dimensionali…
Paper proposes a probabilistic alignment method for domain adaptation.
CCP clusters correlated features and projects them to 1D for efficient dimensionality reduction.
The characteristics (or numerical patterns) of a feature vector in the transform domain of a perturbation model differ significantly from those of its corresponding feature vector in the input domain. These differences - caused by the perturbation techniques used for the transformation of feature patterns - degrade the…
A novel optimization-based Gaussian mixture reduction method using composite transportation divergence.
Paper introduces a new model to handle multi-task learning across different input domains.
We consider time-domain digital backpropagation with chromatic dispersion filters jointly optimized and quantized using machine-learning techniques. Compared to the baseline implementations, we show improved BER performance and >40% power dissipation reductions in 28-nm CMOS.
Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function representing discounted return. In this paper, we examine the role of these policy gradi…
Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains are possible using a single DNN for both speaker and language recognition. The u…
This work compresses sequences by treating them as continuous-time processes, enabling efficient discretization.
New approach avoids excess empirical risk in domain generalization.
New deep network derived from rate reduction principles, explaining features and efficiency.
This report concerns the problem of dimensionality reduction through information geometric methods on statistical manifolds. While there has been considerable work recently presented regarding dimensionality reduction for the purposes of learning tasks such as classification, clustering, and visualization, these method…
New method corrects missing data bias in dimension reduction.
Unsupervised learning of time series data, also known as temporal clustering, is a challenging problem in machine learning. Here we propose a novel algorithm, Deep Temporal Clustering (DTC), to naturally integrate dimensionality reduction and temporal clustering into a single end-to-end learning framework, fully unsupe…
We study the problem of empirical minimization for variance-type functionals over functional classes. Sharp non-asymptotic bounds for the excess variance are derived under mild conditions. In particular, it is shown that under some restrictions imposed on the functional class fast convergence rates can be achieved incl…
We study optimization algorithms based on variance reduction for stochastic gradient descent (SGD). Remarkable recent progress has been made in this direction through development of algorithms like SAG, SVRG, SAGA. These algorithms have been shown to outperform SGD, both theoretically and empirically. However, asynchro…
Unsupervised domain adaptation is a promising way to generalize deep models to novel domains. However, the current literature assumes that the label distribution is domain-invariant and only aligns the feature distributions or vice versa. In this work, we explore the more realistic task of Class-imbalanced Domain Adapt…
The paper examines domain generalization algorithms and finds empirical risk minimization performs well.
A new framework for dimension reduction using ensemble of random projections.
New method improves scalability of SGD for large datasets.
Paper develops efficient algorithms for robust optimization across multiple groups.
Unsupervised domain adaptation aims to generalize the hypothesis trained in a source domain to an unlabeled target domain. One popular approach to this problem is to learn domain-invariant embeddings for both domains. In this work, we study, theoretically and empirically, the effect of the embedding complexity on gener…
We introduce several new black-box reductions that significantly improve the design of adaptive and parameter-free online learning algorithms by simplifying analysis, improving regret guarantees, and sometimes even improving runtime. We reduce parameter-free online learning to online exp-concave optimization, we reduce…
Empirical Bayes improves causal representation learning across multiple domains.
Accelerates signature kernel computation for sequences.
EBQL reduces bias in Q-learning for improved performance.
We derive a closed formula for a star-product on complex projective space and on the domain using a completely elementary construction: Starting from the standard star-product of Wick type on and performing a quantum analogue of Marsden-Weinstein reduction, we ca…
We propose a new randomized ensemble technique with a provable security guarantee against black-box transfer attacks. Our proof constructs a new security problem for random binary classifiers which is easier to empirically verify and a reduction from the security of this new model to the security of the ensemble classi…
Efficient methods reduce projections in non-stationary online learning.
Unified framework for DR and clustering using Gromov-Wasserstein.
We might hope that when faced with unexpected inputs, well-designed software systems would fire off warnings. Machine learning (ML) systems, however, which depend strongly on properties of their inputs (e.g. the i.i.d. assumption), tend to fail silently. This paper explores the problem of building ML systems that fail …
New method reduces label and data shifts between domains using optimal transport.
Direct optimization is an appealing framework that replaces integration with optimization of a random objective for approximating gradients in models with discrete random variables. A sampling is a framework for optimizing such random objectives over large spaces. We show how to combine these techniques to yiel…
A characterization of maximal domains of existence of adapted complex structures for Riemannian homogeneous manifolds under certain extensibility assumptions on their geodesic flow is given. This is applied to generalized Heisenberg groups and naturally reductive Riemannian homogeneous spaces. As an application it is s…
RAD improves robustness to domain annotation noise without explicit domain annotations.