Search Results for author:
Found 37 papers, 12 papers with code
Active Symbolic Discovery of Ordinary Differential Equations via Phase Portrait Sketching
Chaos theory indicates that small changes in the initial conditions of a dynamical system can result in vastly different trajectories, necessitating the maintenance of a large set of initial conditions of the trajectory.
A Tighter Convergence Proof of Reverse Experience Replay
In reinforcement learning, Reverse Experience Replay (RER) is a recently proposed algorithm that attains better sample complexity than the classic experience replay method.
Vertical Symbolic Regression via Deep Policy Gradient
We propose Vertical Symbolic Regression using Deep Policy Gradient (VSR-DPG) and demonstrate that VSR-DPG can recover ground-truth equations involving multiple input variables, significantly beyond both deep reinforcement learning-based approaches and previous VSR variants.
Vertical Symbolic Regression
The first few steps in vertical discovery are significantly cheaper than the horizontal path, as their search is in reduced hypothesis spaces involving a small set of variables.
Hypothesis Network Planned Exploration for Rapid Meta-Reinforcement Learning Adaptation
Meta Reinforcement Learning (Meta RL) trains agents that adapt to fast-changing environments and tasks.
Integrating Symbolic Reasoning into Neural Generative Models for Design Generation
SPRING embeds a neural and symbolic integrated spatial reasoning module inside the deep generative network.
Solving Satisfiability Modulo Counting for Symbolic and Statistical AI Integration With Provable Guarantees
Solving SMC is challenging because of its highly intractable nature($\text{NP}^{\text{PP}}$-complete), incorporating statistical inference and symbolic reasoning.
Racing Control Variable Genetic Programming for Symbolic Regression
A selection scheme similar to that used in selecting good symbolic equations in the genetic programming process is implemented to ensure that promising experiment schedules eventually win over the average ones.
Efficient Learning of PDEs via Taylor Expansion and Sparse Decomposition into Value and Fourier Domains
This decomposition enables efficient learning when the source of the updates consists of gradually changing terms across large areas (sparse in the frequency domain) in addition to a few rapid updates concentrated in a small set of "interfacial" regions (sparse in the value domain).
End-to-end Phase Field Model Discovery Combining Experimentation, Crowdsourcing, Simulation and Learning
Phase-Field-Lab combines (i) a streamlined annotation tool which reduces the annotation time (by ~50-75%), while increasing annotation accuracy compared to baseline; (ii) an end-to-end neural model which automatically learns phase field models from data by embedding phase field simulation and existing domain knowledge into learning; and (iii) novel interfaces and visualizations to integrate our platform into the scientific discovery cycle of domain scientists.
Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning
An additional goal of the generator is to perturb the observation, which maximizes the agent's probability of taking a different action.
Symbolic Regression via Control Variable Genetic Programming
CVGP starts by fitting simple expressions involving a small set of independent variables using genetic programming, under controlled experiments where other variables are held as constants.
Adversarial Policy Optimization in Deep Reinforcement Learning
Data augmentation can provide a performance boost to RL agents by mitigating the effect of overfitting.
Accelerating Policy Gradient by Estimating Value Function from Prior Computation in Deep Reinforcement Learning
Our approach is to estimate the value function from prior computations, such as from the Q-network learned in DQN or the value function trained for different but related environments.
Robust Policy Optimization in Deep Reinforcement Learning
We observed that in many settings, RPO increases the policy entropy early in training and then maintains a certain level of entropy throughout the training period.
Learning Markov Random Fields for Combinatorial Structures via Sampling through Lovász Local Lemma
Contrastive divergence is then applied to separate these samples from those in the training set.
Human-centered XAI for Burn Depth Characterization
Using this framework, we discover that B-mode ultrasound classifiers can be enhanced by supplying textural features.
Bootstrap Advantage Estimation for Policy Optimization in Reinforcement Learning
Unlike using data augmentation on the input to learn value and policy function as existing methods use, our method uses data augmentation to compute a bootstrap advantage estimation.
On the Value of Behavioral Representations for Dense Retrieval
We consider text retrieval within dense representational space in real-world settings such as e-commerce search where (a) document popularity and (b) diversity of queries associated with a document have a skewed distribution.
Bootstrap State Representation using Style Transfer for Better Generalization in Deep Reinforcement Learning
Deep Reinforcement Learning (RL) agents often overfit the training environment, leading to poor generalization performance.
Provable Constrained Stochastic Convex Optimization with XOR-Projected Gradient Descent
Here we propose XOR-PGD, a novel algorithm based on Projected Gradient Descent (PGD) coupled with the XOR sampler, which is guaranteed to solve the constrained stochastic convex optimization problem still in linear convergence rate by choosing proper step size.
LSH-SMILE: Locality Sensitive Hashing Accelerated Simulation and Learning
The advancement of deep neural networks over the last decade has enabled progress in scientific knowledge discovery in the form of learning Partial Differential Equations (PDEs) directly from experiment data.
A Fast Randomized Algorithm for Massive Text Normalization
In addition, FLAN does not require any annotated data or supervised learning.
Adversarial Style Transfer for Robust Policy Optimization in Reinforcement Learning
An additional goal of the generator is to perturb the observation, which maximizes the agent's probability of taking a different action.
Language Generation via Combinatorial Constraint Satisfaction: A Tree Search Enhanced Monte-Carlo Approach
Generating natural language under complex constraints is a principled formulation towards controllable text generation.
Towards Efficient Discrete Integration via Adaptive Quantile Queries
On a suite of UAI inference challenge benchmarks, it saves 81. 5% of WISH queries while retaining the quality of results.
DESK: A Robotic Activity Dataset for Dexterous Surgical Skills Transfer to Medical Robots
It comprises a set of surgical robotic skills collected during a surgical training task using three robotic platforms: the Taurus II robot, Taurus II simulated robot, and the YuMi robot.
Robotics
Expanding Holographic Embeddings for Knowledge Completion
Neural models operating over structured spaces such as knowledge graphs require a continuous embedding of the discrete elements of this space (such as entities) as well as the relationships between them.
End-to-End Refinement Guided by Pre-trained Prototypical Classifier
We propose imitation refinement, a novel approach to refine imperfect input patterns, guided by a pre-trained classifier incorporating prior knowledge from simulated theoretical data, such that the refined patterns imitate the ideal data.
End-to-End Learning for the Deep Multivariate Probit Model
The multivariate probit model (MVP) is a popular classic model for studying binary responses of multiple entities.
Scalable Relaxations of Sparse Packing Constraints: Optimal Biocontrol in Predator-Prey Network
Cascades represent rapid changes in networks.
Multi-Entity Dependence Learning with Rich Context via Conditional Variational Auto-encoder
Multi-Entity Dependence Learning (MEDL) explores conditional correlations among multiple entities.
XOR-Sampling for Network Design with Correlated Stochastic Events
In this paper, we consider a more realistic setting where multiple edges are not independent due to natural disasters or regional events that make the states of multiple edges stochastically correlated.
Solving Marginal MAP Problems with NP Oracles and Parity Constraints
Arising from many applications at the intersection of decision making and machine learning, Marginal Maximum A Posteriori (Marginal MAP) Problems unify the two main classes of inference, namely maximization (optimization) and marginal inference (counting), and are believed to have higher complexity than both of them.
Phase-Mapper: An AI Platform to Accelerate High Throughput Materials Discovery
A key problem in materials discovery, the phase map identification problem, involves the determination of the crystal phase diagram from the materials' composition and structural characterization data.
Deep Multi-Species Embedding
Additionally, we demonstrate the benefit of using a deep neural network to extract features within the embedding and show how they improve the predictive performance of species distribution modelling.
Variable Elimination in the Fourier Domain
The ability to represent complex high dimensional probability distributions in a compact form is one of the key insights in the field of graphical models.
