arXiv research

Algorithm learns decision trees from noisy data.

New algorithm for planning in observable POMDPs in quasi-polynomial time.

The integer hull of a polyhedron is the convex hull of the integer points contained in it. We show that the vertices of the integer hulls of a rational family of polyhedra of size O(n) have quasipolynomial coordinates. As a corollary, we show that the stable commutator length of elements in a surgery family is a ratio …

New algorithms recover signals robustly against outliers and heavy-tailed noise.

We study the fundamental problem of learning the parameters of a high-dimensional Gaussian in the presence of noise -- where an $\varepsilon$-fraction of our samples were chosen by an adversary. We give robust estimators that achieve estimation error $O(\varepsilon)$ in the total variation distance, which is optimal up…

New algorithm learns POMDPs without computational oracles.

Minimizing a convex risk function is the main step in many basic learning algorithms. We study protocols for convex optimization which provably leak very little about the individual data points that constitute the loss function. Specifically, we consider differentially private algorithms that operate in the local model…

New memory-query tradeoffs for convex optimization algorithms.

We study the counting function of topological Poincaré series associated with rational homology sphere plumbed 3-manifold with connected negative definite tree, interpreting as an alternating sum of coefficient functions associated with some Taylor expansions. It is motivated by a theorem of Szenes and Vergne which exp…

We consider two problems that arise in machine learning applications: the problem of recovering a planted sparse vector in a random linear subspace and the problem of decomposing a random low-rank overcomplete 3-tensor. For both problems, the best known guarantees are based on the sum-of-squares method. We develop new …

Polynomial-time algorithm for clustering mixtures with separation Δ=Ω(√(log k)).

In dictionary learning, also known as sparse coding, the algorithm is given samples of the form $y = Ax$ where $x\in \mathbb{R}^m$ is an unknown random sparse vector and $A$ is an unknown dictionary matrix in $\mathbb{R}^{n\times m}$ (usually $m > n$, which is the overcomplete case). The goal is to learn $A$ and $x$. T…

Efficient algorithm for learning halfspaces in a new model with polynomial time complexity.

We introduce the problem of learning mixtures of $k$ subcubes over $\{0,1\}^n$, which contains many classic learning theory problems as a special case (and is itself a special case of others). We give a surprising $n^{O(\log k)}$-time learning algorithm based on higher-order multilinear moments. It is not possible to l…

Analyzes intrinsic time in financial markets, linking it to physical time.

Consider power utility maximization of terminal wealth in a 1-dimensional continuous-time exponential Levy model with finite time horizon. We discretize the model by restricting portfolio adjustments to an equidistant discrete time grid. Under minimal assumptions we prove convergence of the optimal discrete-time strate…

New distances defined between space-times, proving some definite.

Proposes a method to allocate time budgets in mixed criticality systems.

In this paper, we propose two discontinuous dynamical systems in continuous time with guaranteed prescribed finite-time local convergence to strict local minima of a given cost function. Our approach consists of exploiting a Lyapunov-based differential inequality for differential inclusions, which leads to finite-time …

Paper analyzes venture capital exit decisions under inconsistent preferences.

TSMB handles time delays in multivariate time series data.

Modeling regime shifts in co-evolving time series with interactions and time-dependency.

Logarithmic regret for continuous-time reinforcement learning.

We provide the proof that the space of time series data is a Kolmogorov space with $T_{0}$-separation axiom using the loop space of time series data. In our approach we define a cyclic coordinate of intrinsic time scale of time series data after empirical mode decomposition. A spinor field of time series data comes fro…

Recently, it is proven that generalized Robertson-Walker space-times in all orthogonal subspaces of Gray's decomposition but one(unrestricted) are perfect fluid space-times. GRW space-times in the unrestricted subspace are identified by having constant scalar curvature. Generalized quasi-Einstein GRW space-times have a…

We apply the theory of continuous time random walks to study some aspects of the extreme value problem applied to financial time series. We focus our attention on extreme times, specifically the mean exit time and the mean first-passage time. We set the general equations for these extremes and evaluate the mean exit ti…

We investigate the waiting-time distribution of the absolute return in the Korean stock-market index KOSPI. We define the waiting time as a time interval during which the normalized absolute return remains continuously below a threshold $r_c$. Through an exponential bin plot, we observe that the waiting-time distributi…

EDICT learns evidential distributions for irregular time series, improving predictions and uncertainty quantification.

Infinite rank groups found in 3-manifolds with infinite fundamental groups.

Study space-like and time-like surfaces in Robertson-Walker space-times with positive nullity.

OneShotSTL efficiently decomposes time series online, improving speed and accuracy.

Proves compactness for timed-metric spaces using new distance and maps.

The study uses Hidden Markov Models to analyze student enrollment patterns and academic performance.

Compactness theorem for timed-metric spaces established.

Generative profiling improves real-time task timing for varied resource contexts.

This paper introduces intrinsic time, a new measure of time for complex systems.

DTW calculates the similarity or alignment between two signals, subject to temporal warping. However, its computational complexity grows exponentially with the number of time-series. Although there have been algorithms developed that are linear in the number of time-series, they are generally quadratic in time-series l…

To improve the efficient frontier of the classical mean-variance model in continuous time, we propose a varying terminal time mean-variance model with a constraint on the mean value of the portfolio asset, which moves with the varying terminal time. Using the embedding technique from stochastic optimal control in conti…

Proposes GDTW for aligning time series on different, incomparable spaces.

The paper examines isotropic cosmological space-times with changing sectional curvature.

We investigate refocusing and strong refocusing of light rays in a space-time. A strongly refocusing space-time is refocusing. The converse is unknown. We construct examples of space-times which are refocusing, but not strongly so, at a particular point. These space-times are strongly refocusing at other points. The ge…

New bounds for causal effect identification in time series graphs with latent confounders.

The explosion of time series data in recent years has brought a flourish of new time series analysis methods, for forecasting, clustering, classification and other tasks. The evaluation of these new methods requires either collecting or simulating a diverse set of time series benchmarking data to enable reliable compar…

TimeCNN improves forecasting by refining cross-variable interactions over time.

Paper develops a continuous-time framework for financial markets without stochastic calculus.

Continuous time framework for discrete data denoising models.

Time-related features improve time series forecasting models.

An RNN-Survival model predicts optimal email send times based on recipient behavior.