arXiv research

The paper improves collapsing Alexandrov spaces results using good coverings.

We analyze consistency of $α$-Rényi approximate posteriors for Bayesian models.

The paper establishes conditions for optimal sampling configurations on complex manifolds.

There are certain families of words and word sequences (words in the generators of a two-generator group) that arise frequently in the Teichm{ü}ller theory of hyperbolic three-manifolds and Kleinian and Fuchsian groups and in the discreteness problem for two generator matrix groups. We survey some of the families of su…

The Ekeland variational principle implies what can be regarded as a strong version, in the $C^1$ category, of the Yau minimum principle: under the appropriate hypotheses {\it every} minimizing sequence admits a {\it good shadow}, a second minimizing sequence that has good properties and is asymptotic to the original on…

Sequence generative adversarial networks (SeqGAN) have been used to improve conditional sequence generation tasks, for example, chit-chat dialogue generation. To stabilize the training of SeqGAN, Monte Carlo tree search (MCTS) or reward at every generation step (REGS) is used to evaluate the goodness of a generated sub…

Estimates missing mass in Markovian sequences with linear runtime and near-optimal risk.

Develops confidence bounds for off-policy evaluation in contextual bandits.

New framework infers causal shifts in event sequences under out-of-domain interventions.

This paper extends the Good Covering Theorem and Jordan Curve Theorem for proximal Alexandrov spaces.

Machine learning approaches have been effective in predicting adverse outcomes in different clinical settings. These models are often developed and evaluated on datasets with heterogeneous patient populations. However, good predictive performance on the aggregate population does not imply good performance for specific …

Value aggregation is a general framework for solving imitation learning problems. Based on the idea of data aggregation, it generates a policy sequence by iteratively interleaving policy optimization and evaluation in an online learning setting. While the existence of a good policy in the policy sequence can be guarant…

An adversarial detector identifies anomalous sequences in sequential data.

Estimates stationary mass and frequency from non-i.i.d. data.

Novel proof technique for Gelfand-Fuks cohomology.

Kernel methods on discrete domains have shown great promise for many challenging data types, for instance, biological sequence data and molecular structure data. Scalable kernel methods like Support Vector Machines may offer good predictive performances but do not intrinsically provide uncertainty estimates. In contras…

A new kernel Stein test assesses fit for variable-length sequential data.

Understanding optimal prompts for binary sequence predictors is challenging.

New algorithm improves interpretability in sequence classification.

For collapsing sequences of Riemannian manifolds which satisfy a uniform lower Ricci curvature bound it is shown that there is a sequence of scales such that for a set of good base points of large measure the pointed rescaled manifolds subconverge to a product of a Euclidean and a compact space. All Euclidean factors h…

A new method samples sequences without replacement using Gumbel-Top-k trick.

P3BO optimizes biological sequence design by combining multiple methods.

Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even though language has a clear hierarchical structure going from characters throug…

GeNet classifies metagenomic sequences with less memory and comparable recall to state-of-the-art methods.

Using the work of Bonahon-Dreyer and Fock-Goncharov, one can construct a real-analytic parameterization for the PSL(n,R) Hitchin component of a surface S, that is explicitly analogous to the Fenchel-Nielsen coordinates on the Teichmuller space of S. Given a Hitchin representation, we give a lower bound on the "length" …

A statistical physics model for the time evolutions of stock portfolios is proposed. In this model the time series of price changes are coded into the sequences of up and down spins. The Hamiltonian of the system is introduced and is expressed by spin-spin interactions as in spin glass models of disordered magnetic sys…

When learning a hidden Markov model (HMM), sequen- tial observations can often be complemented by real-valued summary response variables generated from the path of hid- den states. Such settings arise in numerous domains, includ- ing many applications in biology, like motif discovery and genome annotation. In this pape…

Despite recent advances in training recurrent neural networks (RNNs), capturing long-term dependencies in sequences remains a fundamental challenge. Most approaches use backpropagation through time (BPTT), which is difficult to scale to very long sequences. This paper proposes a simple method that improves the ability …

Sequence probability predicts correctness in LLMs, but not for repeated prompts

The paper explores how to make neural networks extrapolate longer sequences.

Improved speech recognition with language model integration in sequence-to-sequence models.

Funnel-Transformer reduces computation by compressing sequence data.

New method models longitudinal data using variational inference and normalizing flows.

Study the relationship between canonical polynomials and elliptic sequences for elliptic singularities.

Seq-U-Net improves sequence modeling efficiency with dilated U-Net.

Generative concept representations have three major advantages over discriminative ones: they can represent uncertainty, they support integration of learning and reasoning, and they are good for unsupervised and semi-supervised learning. We discuss probabilistic and generative deep learning, which generative concept re…

We consider the class of compact n-dimensional Riemannian manifolds with cylindrical boundary, Ricci curvature bounded below by a given constant and injectivity radius bounded below by a positive constant, away from the boundary. For a manifold M of this class, we introduce a notion of discretization, leading to a grap…

We present a technique for clustering categorical data by generating many dissimilarity matrices and averaging over them. We begin by demonstrating our technique on low dimensional categorical data and comparing it to several other techniques that have been proposed. Then we give conditions under which our method shoul…

Develops a universal test for assessing dynamic network models.

Derives formula for present value of future consumer goods multiplier.

Develops a method to infer cell trajectories from RNA sequencing data.

RENAL test evaluates generative models for time series data.

In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic forgetting even when they are trained to approximate a single target distribution. We show that GAN training is a continual learning problem in which the sequence of changing model distributions is the sequence of tasks to the d…

Goodwillie's model connects knot spaces to cosimplicial spaces, aiding in knot homotopy computation.

Until recently, research on artificial neural networks was largely restricted to systems with only two types of variable: Neural activities that represent the current or recent input and weights that learn to capture regularities among inputs, outputs and payoffs. There is no good reason for this restriction. Synapses …

The paper shows how heat flow approximates area functional on specific geometric spaces.

Rational kernels offer a way to handle sequence data efficiently.

Study proposes a time-aware model to predict user conversion intent.