Search Results for author: Yexiang Xue

Found 35 papers, 10 papers with code

Vertical Symbolic Regression via Deep Policy Gradient

no code implementations1 Feb 2024 Nan Jiang, Md Nasim, Yexiang Xue

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.

Decision Making regression +1

Vertical Symbolic Regression

no code implementations19 Dec 2023 Nan Jiang, Md Nasim, Yexiang Xue

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.

regression Symbolic Regression

Integrating Symbolic Reasoning into Neural Generative Models for Design Generation

no code implementations13 Oct 2023 Maxwell Joseph Jacobson, Yexiang Xue

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

no code implementations16 Sep 2023 Jinzhao Li, Nan Jiang, Yexiang Xue

Solving SMC is challenging because of its highly intractable nature($\text{NP}^{\text{PP}}$-complete), incorporating statistical inference and symbolic reasoning.

Decision Making

Efficient Learning of PDEs via Taylor Expansion and Sparse Decomposition into Value and Fourier Domains

no code implementations13 Sep 2023 Md Nasim, Yexiang Xue

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

no code implementations13 Sep 2023 Md Nasim, Anter El-Azab, Xinghang Zhang, Yexiang Xue

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.

Model Discovery

Racing Control Variable Genetic Programming for Symbolic Regression

1 code implementation13 Sep 2023 Nan Jiang, Yexiang Xue

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.

regression Symbolic Regression

Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning

no code implementations29 Aug 2023 Md Masudur Rahman, Yexiang Xue

An additional goal of the generator is to perturb the observation, which maximizes the agent's probability of taking a different action.

Data Augmentation reinforcement-learning +1

Symbolic Regression via Control Variable Genetic Programming

1 code implementation25 May 2023 Nan Jiang, Yexiang Xue

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.

regression Symbolic Regression

Adversarial Policy Optimization in Deep Reinforcement Learning

no code implementations27 Apr 2023 Md Masudur Rahman, Yexiang Xue

Data augmentation can provide a performance boost to RL agents by mitigating the effect of overfitting.

Data Augmentation reinforcement-learning

Accelerating Policy Gradient by Estimating Value Function from Prior Computation in Deep Reinforcement Learning

no code implementations2 Feb 2023 Md Masudur Rahman, Yexiang Xue

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.

Policy Gradient Methods

Robust Policy Optimization in Deep Reinforcement Learning

1 code implementation14 Dec 2022 Md Masudur Rahman, Yexiang Xue

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.

Continuous Control Data Augmentation +3

Learning Markov Random Fields for Combinatorial Structures via Sampling through Lovász Local Lemma

1 code implementation1 Dec 2022 Nan Jiang, Yi Gu, Yexiang Xue

Contrastive divergence is then applied to separate these samples from those in the training set.

LEMMA valid

Bootstrap Advantage Estimation for Policy Optimization in Reinforcement Learning

1 code implementation13 Oct 2022 Md Masudur Rahman, Yexiang Xue

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.

Data Augmentation reinforcement-learning +1

On the Value of Behavioral Representations for Dense Retrieval

no code implementations11 Aug 2022 Nan Jiang, Dhivya Eswaran, Choon Hui Teo, Yexiang Xue, Yesh Dattatreya, Sujay Sanghavi, Vishy Vishwanathan

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.

Retrieval Text Retrieval

Provable Constrained Stochastic Convex Optimization with XOR-Projected Gradient Descent

no code implementations22 Mar 2022 Fan Ding, Yijie Wang, Jianzhu Ma, Yexiang Xue

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.

Management

LSH-SMILE: Locality Sensitive Hashing Accelerated Simulation and Learning

no code implementations NeurIPS 2021 Chonghao Sima, Yexiang Xue

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

no code implementations6 Oct 2021 Nan Jiang, Chen Luo, Vihan Lakshman, Yesh Dattatreya, Yexiang Xue

In addition, FLAN does not require any annotated data or supervised learning.

Adversarial Style Transfer for Robust Policy Optimization in Reinforcement Learning

no code implementations29 Sep 2021 Md Masudur Rahman, Yexiang Xue

An additional goal of the generator is to perturb the observation, which maximizes the agent's probability of taking a different action.

reinforcement-learning Reinforcement Learning (RL) +1

Towards Efficient Discrete Integration via Adaptive Quantile Queries

no code implementations13 Oct 2019 Fan Ding, Hanjing Wang, Ashish Sabharwal, Yexiang Xue

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

1 code implementation3 Mar 2019 Naveen Madapana, Md Masudur Rahman, Natalia Sanchez-Tamayo, Mythra V. Balakuntala, Glebys Gonzalez, Jyothsna Padmakumar Bindu, L. N. Vishnunandan Venkatesh, Xingguang Zhang, Juan Barragan Noguera, Thomas Low, Richard Voyles, Yexiang Xue, Juan Wachs

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

no code implementations NeurIPS 2018 Yexiang Xue, Yang Yuan, Zhitian Xu, Ashish Sabharwal

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.

Knowledge Graphs

End-to-End Refinement Guided by Pre-trained Prototypical Classifier

1 code implementation7 May 2018 Junwen Bai, Zihang Lai, Runzhe Yang, Yexiang Xue, John Gregoire, Carla Gomes

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

no code implementations ICML 2018 Di Chen, Yexiang Xue, Carla P. Gomes

The multivariate probit model (MVP) is a popular classic model for studying binary responses of multiple entities.

Multi-Entity Dependence Learning with Rich Context via Conditional Variational Auto-encoder

no code implementations17 Sep 2017 Luming Tang, Yexiang Xue, Di Chen, Carla P. Gomes

Multi-Entity Dependence Learning (MEDL) explores conditional correlations among multiple entities.

XOR-Sampling for Network Design with Correlated Stochastic Events

no code implementations23 May 2017 Xiaojian Wu, Yexiang Xue, Bart Selman, Carla P. Gomes

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

no code implementations NeurIPS 2016 Yexiang Xue, Zhiyuan Li, Stefano Ermon, Carla P. Gomes, Bart Selman

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.

BIG-bench Machine Learning Decision Making

Phase-Mapper: An AI Platform to Accelerate High Throughput Materials Discovery

1 code implementation3 Oct 2016 Yexiang Xue, Junwen Bai, Ronan Le Bras, Brendan Rappazzo, Richard Bernstein, Johan Bjorck, Liane Longpre, Santosh K. Suram, Robert B. van Dover, John Gregoire, Carla P. Gomes

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.

Vocal Bursts Intensity Prediction

Deep Multi-Species Embedding

no code implementations28 Sep 2016 Di Chen, Yexiang Xue, Shuo Chen, Daniel Fink, Carla Gomes

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

no code implementations17 Aug 2015 Yexiang Xue, Stefano Ermon, Ronan Le Bras, Carla P. Gomes, Bart Selman

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.

Cannot find the paper you are looking for? You can Submit a new open access paper.