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.
State-space systems generate probabilistic dependencies between inputs and outputs.
DL-Droid detects Android malware using deep learning and real devices.
Generalizes memory and forecasting capacities for nonlinear recurrent networks with dependent inputs.
Quantum Process Tomography (QPT) methods aim at identifying, i.e. estimating, a given quantum process. QPT is a major quantum information processing tool, since it especially allows one to characterize the actual behavior of quantum gates, which are the building blocks of quantum computers. However, usual QPT procedure…
Paper shows how to linearize flat systems with two inputs.
We present a novel framework for specifying and verifying correctness globally for neural networks on perception tasks. Most previous works on neural network verification for perception tasks focus on robustness verification. Unlike robustness verification, which aims to verify that the prediction of a network is stabl…
We consider reinforcement learning in input-driven environments, where an exogenous, stochastic input process affects the dynamics of the system. Input processes arise in many applications, including queuing systems, robotics control with disturbances, and object tracking. Since the state dynamics and rewards depend on…
The problem of combined state and input estimation of linear structural systems based on measured responses and a priori knowledge of structural model is considered. A novel methodology using Gaussian process latent force models is proposed to tackle the problem in a stochastic setting. Gaussian process latent force mo…
The paper is devoted to the local classification of generic control-affine systems on an n-dimensional manifold with scalar input for any n>3 or with two inputs for n=4 and n=5, up to state-feedback transformations, preserving the affine structure. First using the Poincare series of moduli numbers we introduce the intr…
URNNs are as expressive as general RNNs with ReLU activations.
ContextBench benchmarks methods for generating linguistically fluent inputs that activate specific latent features in language models.
New method uses explicit human demonstrations to teach missing features in reward learning.
PredPCA extracts key components for better time series prediction.
Improves LSTM performance by initializing states via manifold learning.
ETC improves Transformer models for long and structured inputs.
Active learning selects inputs for GPSSM to learn latent states.
Parameterized state space models in the form of recurrent networks are often used in machine learning to learn from data streams exhibiting temporal dependencies. To break the black box nature of such models it is important to understand the dynamical features of the input driving time series that are formed in the sta…
Recent breakthroughs in computer vision and natural language processing have spurred interest in challenging multi-modal tasks such as visual question-answering and visual dialogue. For such tasks, one successful approach is to condition image-based convolutional network computation on language via Feature-wise Linear …
I-BERT extends Transformer's self-attention to arbitrary input lengths.
Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some norm. Although studying these attacks is valuable, there has been increasing interest in the construction of (and robustness to) unrestricted…
State-of-the-art deep neural networks (DNNs) are highly effective in solving many complex real-world problems. However, these models are vulnerable to adversarial perturbation attacks, and despite the plethora of research in this domain, to this day, adversaries still have the upper hand in the cat and mouse game of ad…
ENRNN uses eigenvalue normalization for short-term memory in RNNs.
Improved RL for grasping in cluttered scenes using state representation learning.
Machine learning has recently emerged as a fruitful area for finding potential quantum computational advantage. Many of the quantum enhanced machine learning algorithms critically hinge upon the ability to efficiently produce states proportional to high-dimensional data points stored in a quantum accessible memory. Eve…
D2D-SPL uses discrete states and a classifier to train RL faster.
Deep reinforcement learning (DRL) has shown incredible performance in learning various tasks to the human level. However, unlike human perception, current DRL models connect the entire low-level sensory input to the state-action values rather than exploiting the relationship between and among entities that constitute t…
Embeddings leak sensitive information about input data, which can be recovered or inferred.
Robust method estimates state, input, and parameters of linear systems online.
Fairness is a critical trait in decision making. As machine-learning models are increasingly being used in sensitive application domains (e.g. education and employment) for decision making, it is crucial that the decisions computed by such models are free of unintended bias. But how can we automatically validate the fa…
Study stability of selective SSMs with discontinuous gating.
RISE framework unifies and improves time series learning with missing data.
New findings on flatness for specific driftless systems.
New insights into how encoder-decoder networks generate attention matrices.
Traditional GANs use a deterministic generator function (typically a neural network) to transform a random noise input to a sample that the discriminator seeks to distinguish. We propose a new GAN called Bayesian Conditional Generative Adversarial Networks (BC-GANs) that use a random generator function…
Proposes training neural networks to predict uncertainty for out-of-distribution inputs.
Adversarial attacks on deep neural networks traditionally rely on a constrained optimization paradigm, where an optimization procedure is used to obtain a single adversarial perturbation for a given input example. In this work we frame the problem as learning a distribution of adversarial perturbations, enabling us to …
We introduce a Gaussian process model of functions which are additive. An additive function is one which decomposes into a sum of low-dimensional functions, each depending on only a subset of the input variables. Additive GPs generalize both Generalized Additive Models, and the standard GP models which use squared-expo…
This research investigates reliable local explanations for machine listening models.
A dynamical system can be regarded as an information processing apparatus that encodes input streams from the external environment to its state and processes them through state transitions. The information processing capacity (IPC) is an excellent tool that comprehensively evaluates these processed inputs, providing de…
Paper proposes a method to generate adversarial perturbations for black-box attacks without accessing inner states.
Paper proposes a dual-level approach for multi-step forecasting of dynamical systems.
Entangled bisimulation improves policy learning from visual input.
Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally masking high attribution features. We study the robustness of machine learning model…
Spin-opstrings from QMC simulations enable ML of quantum phases.
Recurrent neural networks (RNNs) have drawn interest from machine learning researchers because of their effectiveness at preserving past inputs for time-varying data processing tasks. To understand the success and limitations of RNNs, it is critical that we advance our analysis of their fundamental memory properties. W…
Given a classical channel---a stochastic map from inputs to outputs---the input can often be transformed to an intermediate variable that is informationally smaller than the input. The new channel accurately simulates the original but at a smaller transmission rate. Here, we examine this procedure when the intermediate…
We study the impact of input noise dimension on GAN performance.
Increasing input dimensionality improves deep RL performance and sample efficiency.