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.
Illustrates interleaved learning with Kalman Filter for linear least squares.
Formula for interleaving distance of rectangle persistence modules.
Paper proposes a new model and methods for robustly de-interleaving HMP mixtures.
Automates reparameterization in probabilistic programs for better inference.
The paper tightens bounds on distances between Reeb graphs.
Study exact Lagrangian cobordisms in cotangent bundles, proving bounds on sheaf interleaving distance and shadow distance.
Study integrates attentional and spacing factors to improve category learning models.
Interleaved RNNs detect fraud without costly features.
Stable density-based clustering via multiparameter persistence.
Improved hybrid acoustic model using interleaved self-attention and convolution.
Improves text-to-speech speed by interleaving character reading and audio synthesis.
DNA rearrangement processes recombine gene segments that are organized on the chromosome in a variety of ways. The segments can overlap, interleave or one may be a subsegment of another. We use directed graphs to represent segment organizations on a given locus where contigs containing rearranged segments represent ver…
Many of our core assumptions about how neural networks operate remain empirically untested. One common assumption is that convolutional neural networks need to be stable to small translations and deformations to solve image recognition tasks. For many years, this stability was baked into CNN architectures by incorporat…
DeepDIVE disentangles input into marginal and conditional distributions for multi-task learning.
Invariants measure letter interleaving in groups, detecting group dimensions.
The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or continual fashion. Current solutions to the continual learning problem require experie…
On-policy reinforcement learning (RL) algorithms have high sample complexity while off-policy algorithms are difficult to tune. Merging the two holds the promise to develop efficient algorithms that generalize across diverse environments. It is however challenging in practice to find suitable hyper-parameters that gove…
Unified model integrates text and time series for financial forecasting.
In this paper, we propose a fully supervised speaker diarization approach, named unbounded interleaved-state recurrent neural networks (UIS-RNN). Given extracted speaker-discriminative embeddings (a.k.a. d-vectors) from input utterances, each individual speaker is modeled by a parameter-sharing RNN, while the RNN state…
HOMER learns latent states to explore rich environments efficiently.
In many practical problems, a learning agent may want to learn the best action in hindsight without ever taking a bad action, which is significantly worse than the default production action. In general, this is impossible because the agent has to explore unknown actions, some of which can be bad, to learn better action…
New model-free algorithms learn representations for low-rank MDPs efficiently.
In the field of exploratory data mining, local structure in data can be described by patterns and discovered by mining algorithms. Although many solutions have been proposed to address the redundancy problems in pattern mining, most of them either provide succinct pattern sets or take the interests of the user into acc…
Learning linear combinations of multiple kernels is an appealing strategy when the right choice of features is unknown. Previous approaches to multiple kernel learning (MKL) promote sparse kernel combinations to support interpretability and scalability. Unfortunately, this 1-norm MKL is rarely observed to outperform tr…
ForecastNet uses a time-variant deep feed-forward neural network for better multi-step-ahead time series forecasting.
Sample efficiency is critical in solving real-world reinforcement learning problems, where agent-environment interactions can be costly. Imitation learning from expert advice has proved to be an effective strategy for reducing the number of interactions required to train a policy. Online imitation learning, which inter…
Recent sequential pattern mining methods have used the minimum description length (MDL) principle to define an encoding scheme which describes an algorithm for mining the most compressing patterns in a database. We present a novel subsequence interleaving model based on a probabilistic model of the sequence database, w…
We propose and analyze a new family of algorithms for training neural networks with ReLU activations. Our algorithms are based on the technique of alternating minimization: estimating the activation patterns of each ReLU for all given samples, interleaved with weight updates via a least-squares step. The main focus of …
A standard way of approximating or discretizing a metric space is by taking its Rips complexes. These approximations for all parameters are often bound together into a filtration, to which we apply the fundamental group or the first homology. We call the resulting object persistence. Recent results demonstrate that per…
Coordinate descent methods usually minimize a cost function by updating a random decision variable (corresponding to one coordinate) at a time. Ideally, we would update the decision variable that yields the largest decrease in the cost function. However, finding this coordinate would require checking all of them, which…
New method predicts state evolution for non-first-order algorithms on nonconvex problems.
ICQ improves high-dimensional similarity search without sacrificing precision.
RPI combines imitation and reinforcement learning to improve policies efficiently.
Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel model for this problem that uses a graph to represent the intermediate state of the generated output. T…
We study the explore-exploit tradeoff in distributed cooperative decision-making using the context of the multiarmed bandit (MAB) problem. For the distributed cooperative MAB problem, we design the cooperative UCB algorithm that comprises two interleaved distributed processes: (i) running consensus algorithms for estim…
We consider the setting of Reeb graphs of piecewise linear functions and study distances between them that are stable, meaning that functions which are similar in the supremum norm ought to have similar Reeb graphs. We define an edit distance for Reeb graphs and prove that it is stable and universal, meaning that it pr…
Improved exploration algorithm for unknown MDPs with reduced sample complexity.
We propose an alternative framework to existing setups for controlling false alarms when multiple A/B tests are run over time. This setup arises in many practical applications, e.g. when pharmaceutical companies test new treatment options against control pills for different diseases, or when internet companies test the…
Stream deinterleaving is an important problem with various applications in the cybersecurity domain. In this paper, we consider the specific problem of deinterleaving DNS data streams using machine-learning techniques, with the objective of automating the extraction of malware domain sequences. We first develop a gener…
Unified framework connects deformation theory and derived categories for multiparameter persistence.
We describe computationally efficient methods for learning mixtures in which each component is a directed acyclic graphical model (mixtures of DAGs or MDAGs). We argue that simple search-and-score algorithms are infeasible for a variety of problems, and introduce a feasible approach in which parameter and structure sea…
Time-resolved angiography with interleaved stochastic trajectories (TWIST) has been widely used for dynamic contrast enhanced MRI (DCE-MRI). To achieve highly accelerated acquisitions, TWIST combines the periphery of the k-space data from several adjacent frames to reconstruct one temporal frame. However, this view-sha…
Asynchronous framework speeds up model-based RL to real-time.
BREMEN optimizes policies offline with fewer data, achieving efficient deployment.
We consider high-dimensional distribution estimation through autoregressive networks. By combining the concepts of sparsity, mixtures and parameter sharing we obtain a simple model which is fast to train and which achieves state-of-the-art or better results on several standard benchmark datasets. Specifically, we use a…
New algorithm optimizes exploration in unknown MDPs.
A new federated learning framework for handling device heterogeneity.
A core novelty of Alpha Zero is the interleaving of tree search and deep learning, which has proven very successful in board games like Chess, Shogi and Go. These games have a discrete action space. However, many real-world reinforcement learning domains have continuous action spaces, for example in robotic control, na…