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.
High-dimensional unimodal distributions can cause MCMC methods to fail.
Efficient method for learning continuous exponential families beyond Gaussian.
Improved algorithm finds second-order stationary points in non-convex optimization.
New algorithm speeds up polynomial kernel approximations.
Polynomial-time algorithm estimates mean with bounded covariance using differential privacy.
New insights into training ReLU networks, especially as data dimensionality increases.
Polynomial-time algorithm estimates edge density of random graphs with privacy and robustness.
Efficient algorithms improve learning of large-margin halfspaces.
Efficiently learns complex Boolean functions under Gaussian distributions.
Algorithm efficiently learns deep ReLU networks with polynomial runtime in depth and parameters.
Randomly chosen support makes sparse linear regression easy.
Efficiently estimates binary product distributions with privacy.
We study the problem of learning an unknown mixture of rankings over elements, given access to noisy samples drawn from the unknown mixture. We consider a range of different noise models, including natural variants of the "heat kernel" noise framework and the Mallows model. For each of these noise models we giv…
We propose a new method for robust PCA -- the task of recovering a low-rank matrix from sparse corruptions that are of unknown value and support. Our method involves alternating between projecting appropriate residuals onto the set of low-rank matrices, and the set of sparse matrices; each projection is {\em non-convex…
We address the problem of learning in an online setting where the learner repeatedly observes features, selects among a set of actions, and receives reward for the action taken. We provide the first efficient algorithm with an optimal regret. Our algorithm uses a cost sensitive classification learner as an oracle and h…
Accurate estimation of the run time of computational codes has a number of significant advantages for scientific computing. It is required information for optimal resource allocation, improving turnaround times and utilization of science gateways. Furthermore, it allows users to better plan and schedule their research,…
New algorithms learn graph structures privately, matching best results.
Deep architecture such as hierarchical semi-Markov models is an important class of models for nested sequential data. Current exact inference schemes either cost cubic time in sequence length, or exponential time in model depth. These costs are prohibitive for large-scale problems with arbitrary length and depth. In th…
In this paper, we have proposed a deep quantum SVM formulation, and further demonstrated a quantum-clustering framework based on the quantum deep SVM formulation, deep convolutional neural networks, and quantum K-Means clustering. We have investigated the run time computational complexity of the proposed quantum deep c…
We propose a representation of graph as a functional object derived from the power iteration of the underlying adjacency matrix. The proposed functional representation is a graph invariant, i.e., the functional remains unchanged under any reordering of the vertices. This property eliminates the difficulty of handling e…
New method reduces neural image compression run-time by 50%.
A typical census of 3-manifolds contains all manifolds (under various constraints) that can be triangulated with at most n tetrahedra. Al- though censuses are useful resources for mathematicians, constructing them is difficult: the best algorithms to date have not gone beyond n = 12. The underlying algorithms essential…
The paper proposes using function approximations to reduce the computational burden in measuring counterparty credit exposure.
Improved SVRG for quadratic functions achieves better performance and running times.
In this work, we address the problem of tuning communication libraries by using a deep reinforcement learning approach. Reinforcement learning is a machine learning technique incredibly effective in solving game-like situations. In fact, tuning a set of parameters in a communication library in order to get better perfo…
FOLKLORE algorithm speeds up online multiclass logistic regression.
Normal and almost normal surfaces are essential tools for algorithmic 3-manifold topology, but to use them requires exponentially slow enumeration algorithms in a high-dimensional vector space. The quadrilateral coordinates of Tollefson alleviate this problem considerably for normal surfaces, by reducing the dimension …
Recurrent neural networks can be large and compute-intensive, yet many applications that benefit from RNNs run on small devices with very limited compute and storage capabilities while still having run-time constraints. As a result, there is a need for compression techniques that can achieve significant compression wit…
We study -GenEV, the problem of finding the top generalized eigenvectors, and -CCA, the problem of finding the top vectors in canonical-correlation analysis. We propose algorithms and to solve the two problems with running times linearly dependent on the input size and…
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…
Recurrent tasks such as pricing, calibration and risk assessment need to be executed accurately and in real-time. Simultaneously we observe an increase in model sophistication on the one hand and growing demands on the quality of risk management on the other. To address the resulting computational challenges, it is nat…
We present an approximation scheme for support vector machine models that use an RBF kernel. A second-order Maclaurin series approximation is used for exponentials of inner products between support vectors and test instances. The approximation is applicable to all kernel methods featuring sums of kernel evaluations and…
Belief propagation and its variants are popular methods for approximate inference, but their running time and even their convergence depend greatly on the schedule used to send the messages. Recently, dynamic update schedules have been shown to converge much faster on hard networks than static schedules, namely the res…
Long short-term memory (LSTM) has been widely used for sequential data modeling. Researchers have increased LSTM depth by stacking LSTM cells to improve performance. This incurs model redundancy, increases run-time delay, and makes the LSTMs more prone to overfitting. To address these problems, we propose a hidden-laye…
We show that the class of strongly connected graphical models with treewidth at most k can be properly efficiently PAC-learnt with respect to the Kullback-Leibler Divergence. Previous approaches to this problem, such as those of Chow ([1]), and Ho gen ([7]) have shown that this class is PAC-learnable by reducing it to …
We consider the problem of deciding whether a polygonal knot in 3-dimensional Euclidean space is unknotted, capable of being continuously deformed without self-intersection so that it lies in a plane. We show that this problem, {\sc unknotting problem} is in {\bf NP}. We also consider the problem, {\sc unknotting probl…
In the paper, we focus on complexity of C5.0 algorithm for constructing decision tree classifier that is the models for the classification problem from machine learning. In classical case the decision tree is constructed in running time, where is a number of classes, is the size of a traini…
We propose a new method for learning from a single demonstration to solve hard exploration tasks like the Atari game Montezuma's Revenge. Instead of imitating human demonstrations, as proposed in other recent works, our approach is to maximize rewards directly. Our agent is trained using off-the-shelf reinforcement lea…
Improved K-Means++ and K-Means with faster run-time.
Algorithm learns mixtures of linear regressions in subexponential time.
We give the first algorithm for Matrix Completion whose running time and sample complexity is polynomial in the rank of the unknown target matrix, linear in the dimension of the matrix, and logarithmic in the condition number of the matrix. To the best of our knowledge, all previous algorithms either incurred a quadrat…
The anomaly detection of time series is a hotspot of time series data mining. The own characteristics of different anomaly detectors determine the abnormal data that they are good at. There is no detector can be optimizing in all types of anomalies. Moreover, it still has difficulties in industrial production due to pr…
Algorithms compute topological info about curves in surfaces.
This work bounds the run-time of nonconvex optimization with early stopping.
We describe two techniques that significantly improve the running time of several standard machine-learning algorithms when data is sparse. The first technique is an algorithm that effeciently extracts one-way and two-way counts--either real or expected-- from discrete data. Extracting such counts is a fundamental step…
In this paper, we consider efficient differentially private empirical risk minimization from the viewpoint of optimization algorithms. For strongly convex and smooth objectives, we prove that gradient descent with output perturbation not only achieves nearly optimal utility, but also significantly improves the running …
K-nearest neighbor (kNN) search has wide applications in many areas, including data mining, machine learning, statistics and many applied domains. Inspired by the success of ensemble methods and the flexibility of tree-based methodology, we propose random projection forests (rpForests), for kNN search. rpForests finds …
EKM solves the K-medoids problem in polynomial time.