Search Results for author:
Found 29 papers, 9 papers with code
MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
This paper addresses the challenge of optimizing meta-parameters (i. e., hyperparameters) in machine learning algorithms, a critical factor influencing training efficiency and model performance.
Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Data
We provide a candidate intervention target set which is a superset of the true intervention targets.
Efficiently Escaping Saddle Points for Non-Convex Policy Optimization
Policy gradient (PG) is widely used in reinforcement learning due to its scalability and good performance.
Fast Causal Orientation Learning in Directed Acyclic Graphs
In particular, we show that these functions have some desirable properties, enabling us to speed up the process of applying Meek rules.
Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function
We prove that the total sample complexity of SCRN in achieving $\epsilon$-global optimum is $\mathcal{O}(\epsilon^{-7/(2\alpha)+1})$ for $1\le\alpha< 3/2$ and $\mathcal{\tilde{O}}(\epsilon^{-2/(\alpha)})$ for $3/2\le\alpha\le 2$.
A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models
We study experiment design for unique identification of the causal graph of a simple SCM, where the graph may contain cycles.
Momentum-Based Policy Gradient with Second-Order Information
SHARP algorithm is parameter-free, achieving $\epsilon$-approximate first-order stationary point with $O(\epsilon^{-3})$ number of trajectories, while using a batch size of $O(1)$ at each iteration.
Causal Imitative Model for Autonomous Driving
CIM explicitly discovers the causal model and utilizes it to train the policy.
Order Optimal Bounds for One-Shot Federated Learning over non-Convex Loss Functions
We then prove that this lower bound is order optimal in $m$ and $n$ by presenting a distributed learning algorithm, called Multi-Resolution Estimator for Non-Convex loss function (MRE-NC), whose expected loss matches the lower bound for large $mn$ up to polylogarithmic factors.
Deep-Learning Based Blind Recognition of Channel Code Parameters over Candidate Sets under AWGN and Multi-Path Fading Conditions
We consider the problem of recovering channel code parameters over a candidate set by merely analyzing the received encoded signals.
Active Learning of Causal Structures with Deep Reinforcement Learning
We study the problem of experiment design to learn causal structures from interventional data.
Multi Variable-layer Neural Networks for Decoding Linear Codes
In this paper, we introduce a new network architecture by increasing the number of variable-node layers, while keeping the check-node layers unchanged.
LazyIter: A Fast Algorithm for Counting Markov Equivalent DAGs and Designing Experiments
We utilize the proposed method for computing MEC sizes and experiment design in active and passive learning settings.
Bounds on Over-Parameterization for Guaranteed Existence of Descent Paths in Shallow ReLU Networks
We show that there exist poor local minima with positive curvature for some training sets of size $n\geq m+2d-2$.
Order Optimal One-Shot Distributed Learning
We propose an algorithm called Multi-Resolution Estimator (MRE) whose expected error is no larger than $\tilde{O}\big(m^{-{1}/{\max(d, 2)}} n^{-1/2}\big)$, where $d$ is the dimension of the parameter space.
Distributed Voting in Beep Model
For the second algorithm, we show that it returns the correct output with high probability.
Distributed Voting
Distributed, Parallel, and Cluster Computing
Quantitative Methods
Interventional Experiment Design for Causal Structure Learning
For this case, we propose an efficient exact algorithm for the worst-case gain setup, as well as an approximate algorithm for the average gain setup.
Adversarial Orthogonal Regression: Two non-Linear Regressions for Causal Inference
We propose two nonlinear regression methods, named Adversarial Orthogonal Regression (AdOR) for additive noise models and Adversarial Orthogonal Structural Equation Model (AdOSE) for the general case of structural equation models.
Learning Linear Non-Gaussian Causal Models in the Presence of Latent Variables
It can be shown that causal effects among observed variables cannot be identified uniquely even under the assumptions of faithfulness and non-Gaussianity of exogenous noises.
One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Them
We investigate the impact of communication constraint, $B$, on the expected error and derive a tight lower bound on the error achievable by any algorithm.
cuPC: CUDA-based Parallel PC Algorithm for Causal Structure Learning on GPU
The main goal in many fields in the empirical sciences is to discover causal relationships among a set of variables from observational data.
Counting and Sampling from Markov Equivalent DAGs Using Clique Trees
In this paper, we propose a new technique for counting the number of DAGs in a Markov equivalence class.
Budgeted Experiment Design for Causal Structure Learning
We study the problem of causal structure learning when the experimenter is limited to perform at most $k$ non-adaptive experiments of size $1$.
Learning Causal Structures Using Regression Invariance
We study causal inference in a multi-environment setting, in which the functional relations for producing the variables from their direct causes remain the same across environments, while the distribution of exogenous noises may vary.
Token-based Function Computation with Memory
In this paper, we propose a novel token-based approach to compute a wide class of target functions to which we refer as "Token-based function Computation with Memory" (TCM) algorithm.
Distributed Voting/Ranking with Optimal Number of States per Node
Considering a network with $n$ nodes, where each node initially votes for one (or more) choices out of $K$ possible choices, we present a Distributed Multi-choice Voting/Ranking (DMVR) algorithm to determine either the choice with maximum vote (the voting problem) or to rank all the choices in terms of their acquired votes (the ranking problem).
Learning Vector Autoregressive Models with Latent Processes
We show that the support of transition matrix among the observed processes and lengths of all latent paths between any two observed processes can be identified successfully under some conditions on the VAR model.
Optimal Experiment Design for Causal Discovery from Fixed Number of Experiments
We study the problem of causal structure learning over a set of random variables when the experimenter is allowed to perform at most $M$ experiments in a non-adaptive manner.
Identifying Nonlinear 1-Step Causal Influences in Presence of Latent Variables
We propose an approach for learning the causal structure in stochastic dynamical systems with a $1$-step functional dependency in the presence of latent variables.
