Search Results for author:
Found 65 papers, 21 papers with code
A resource-constrained stochastic scheduling algorithm for homeless street outreach and gleaning edible food
We developed a common algorithmic solution addressing the problem of resource-constrained outreach encountered by social change organizations with different missions and operations: Breaking Ground -- an organization that helps individuals experiencing homelessness in New York transition to permanent housing and Leket -- the national food bank of Israel that rescues food from farms and elsewhere to feed the hungry.
Score-based Causal Representation Learning: Linear and General Transformations
The paper addresses both the identifiability and achievability aspects.
General Identifiability and Achievability for Causal Representation Learning
For identifiability, the paper establishes that perfect recovery of the latent causal model and variables is guaranteed under uncoupled interventions.
Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation
We then use Belief Propagation (BP) to marginalize the Gibbs distribution to obtain pseudo labels.
Fairness under Covariate Shift: Improving Fairness-Accuracy tradeoff with few Unlabeled Test Samples
Our third contribution is theoretical, where we show that our weighted entropy term along with prediction loss on the training set approximates test loss under covariate shift.
Identifiability Guarantees for Causal Disentanglement from Soft Interventions
Causal disentanglement aims to uncover a representation of data using latent variables that are interrelated through a causal model.
Optimal Best-Arm Identification in Bandits with Access to Offline Data
Learning paradigms based purely on offline data as well as those based solely on sequential online learning have been well-studied in the literature.
InfoNCE Loss Provably Learns Cluster-Preserving Representations
The goal of contrasting learning is to learn a representation that preserves underlying clusters by keeping samples with similar content, e. g. the ``dogness'' of a dog, close to each other in the space generated by the representation.
Score-based Causal Representation Learning with Interventions
The objectives are: (i) recovering the unknown linear transformation (up to scaling) and (ii) determining the directed acyclic graph (DAG) underlying the latent variables.
Optimal Algorithms for Latent Bandits with Cluster Structure
Instead, we propose LATTICE (Latent bAndiTs via maTrIx ComplEtion) which allows exploitation of the latent cluster structure to provide the minimax optimal regret of $\widetilde{O}(\sqrt{(\mathsf{M}+\mathsf{N})\mathsf{T}})$, when the number of clusters is $\widetilde{O}(1)$.
Selective classification using a robust meta-learning approach
Predictive uncertainty-a model's self awareness regarding its accuracy on an input-is key for both building robust models via training interventions and for test-time applications such as selective classification.
Causal Bandits for Linear Structural Equation Models
Two linear mechanisms, one soft intervention and one observational, are assumed for each node, giving rise to $2^N$ possible interventions.
Causal Graphs Underlying Generative Models: Path to Learning with Limited Data
In this work, we provide a simple algorithm that relies on perturbation experiments on latent codes of a pre-trained generative autoencoder to uncover a causal graph that is implied by the generative model.
PAC Generalization via Invariant Representations
These are representations of the covariates such that the best model on top of the representation is invariant across training environments.
Fourier Representations for Black-Box Optimization over Categorical Variables
In order to improve the performance and sample efficiency of such algorithms, we propose to use existing methods in conjunction with a surrogate model for the black-box evaluations over purely categorical variables.
Auto-Transfer: Learning to Route Transferrable Representations
Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labeled data can be difficult to obtain in many applications.
CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions
We experiment on nonlinear synthetic functions and are able to accurately model as well as estimate feature attributions and even higher order terms in some cases, which is a testament to the representational power as well as interpretability of such architectures.
Scalable Intervention Target Estimation in Linear Models
This paper considers the problem of estimating the unknown intervention targets in a causal directed acyclic graph from observational and interventional data.
Auto-Transfer: Learning to Route Transferable Representations
Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labelled data can be difficult to obtain in many applications.
AI Explainability 360: Impact and Design
As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations.
Episodic Bandits with Stochastic Experts
The agent interacts with the environment over episodes, with each episode having different context distributions; this results in the `best expert' changing across episodes.
Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators
Our key step is to show that the generalized Bellman operator is simultaneously a contraction mapping with respect to a weighted $\ell_p$-norm for each $p$ in $[1,\infty)$, with a common contraction factor.
Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge
Our main result strengthens these prior results by showing that under a different expert-driven structural knowledge -- that one variable is a direct causal parent of treatment variable -- remarkably, testing for subsets (not involving the known parent variable) that are valid back-doors is equivalent to an invariance test.
Treatment Effect Estimation using Invariant Risk Minimization
Inferring causal individual treatment effect (ITE) from observational data is a challenging problem whose difficulty is exacerbated by the presence of treatment assignment bias.
Efficient Encrypted Inference on Ensembles of Decision Trees
In this work, we propose a framework to transfer knowledge extracted by complex decision tree ensembles to shallow neural networks (referred to as DTNets) that are highly conducive to encrypted inference.
A Lyapunov Theory for Finite-Sample Guarantees of Asynchronous Q-Learning and TD-Learning Variants
As a by-product, by analyzing the convergence bounds of $n$-step TD and TD$(\lambda)$, we provide theoretical insights into the bias-variance trade-off, i. e., efficiency of bootstrapping in RL.
Active Structure Learning of Causal DAGs via Directed Clique Trees
Most existing works focus on \textit{worst-case} or \textit{average-case} lower bounds for the number of interventions required to orient a DAG.
Causal Discovery from Soft Interventions with Unknown Targets: Characterization and Learning
One fundamental problem in the empirical sciences is of reconstructing the causal structure that underlies a phenomenon of interest through observation and experimentation.
Stochastic Linear Bandits with Protected Subspace
We study a variant of the stochastic linear bandit problem wherein we optimize a linear objective function but rewards are accrued only orthogonal to an unknown subspace (which we interpret as a \textit{protected space}) given only zero-order stochastic oracle access to both the objective itself and protected subspace.
Active Structure Learning of Causal DAGs via Directed Clique Tree
Most existing works focus on worst-case or average-case lower bounds for the number of interventions required to orient a DAG.
Empirical or Invariant Risk Minimization? A Sample Complexity Perspective
Recently, invariant risk minimization (IRM) was proposed as a promising solution to address out-of-distribution (OOD) generalization.
Linear Regression Games: Convergence Guarantees to Approximate Out-of-Distribution Solutions
In Ahuja et al., it was shown that solving for the Nash equilibria of a new class of "ensemble-games" is equivalent to solving IRM.
Causal Feature Selection for Algorithmic Fairness
In this work, we consider fairness in the integration component of data management, aiming to identify features that improve prediction without adding any bias to the dataset.
Combinatorial Black-Box Optimization with Expert Advice
We consider the problem of black-box function optimization over the boolean hypercube.
A Multi-Channel Neural Graphical Event Model with Negative Evidence
Event datasets are sequences of events of various types occurring irregularly over the time-line, and they are increasingly prevalent in numerous domains.
Learning Global Transparent Models Consistent with Local Contrastive Explanations
Based on a key insight we propose a novel method where we create custom boolean features from sparse local contrastive explanations of the black-box model and then train a globally transparent model on just these, and showcase empirically that such models have higher local consistency compared with other known strategies, while still being close in performance to models that are trained with access to the original data.
On Under-exploration in Bandits with Mean Bounds from Confounded Data
We study a variant of the multi-armed bandit problem where side information in the form of bounds on the mean of each arm is provided.
Invariant Risk Minimization Games
The standard risk minimization paradigm of machine learning is brittle when operating in environments whose test distributions are different from the training distribution due to spurious correlations.
Finite-Sample Analysis of Stochastic Approximation Using Smooth Convex Envelopes
In particular, we use it to establish the first-known convergence rate of the V-trace algorithm for off-policy TD-learning.
Characterization and Learning of Causal Graphs with Latent Variables from Soft Interventions
We introduce a novel notion of interventional equivalence class of causal graphs with latent variables based on these invariances, which associates each graphical structure with a set of interventional distributions that respect the do-calculus rules.
Sample Efficient Active Learning of Causal Trees
We consider the problem of experimental design for learning causal graphs that have a tree structure.
Differentially Private Distributed Data Summarization under Covariate Shift
Our central result is a novel protocol that (a) ensures the curator accesses at most $O(K^{\frac{1}{3}}|D_s| + |D_v|)$ points (b) has formal privacy guarantees on the leakage of information between the data owners and (c) closely matches the best known non-private greedy algorithm.
Leveraging Simple Model Predictions for Enhancing its Performance
Our method also leverages the per sample hardness estimate of the simple model which is not the case with the prior works which primarily consider the complex model's confidences/predictions and is thus conceptually novel.
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of explanation methods, not only those in the toolkit but also in the broader literature on explainability.
Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions
We consider a covariate shift problem where one has access to several different training datasets for the same learning problem and a small validation set which possibly differs from all the individual training distributions.
Model Agnostic Contrastive Explanations for Structured Data
Recently, a method [7] was proposed to generate contrastive explanations for differentiable models such as deep neural networks, where one has complete access to the model.
Enhancing Simple Models by Exploiting What They Already Know
Our method also leverages the per sample hardness estimate of the simple model which is not the case with the prior works which primarily consider the complex model's confidences/predictions and is thus conceptually novel.
Leveraging Latent Features for Local Explanations
As the application of deep neural networks proliferates in numerous areas such as medical imaging, video surveillance, and self driving cars, the need for explaining the decisions of these models has become a hot research topic, both at the global and local level.
Size of Interventional Markov Equivalence Classes in Random DAG Models
For constant density, we show that the expected $\log$ observational MEC size asymptotically (in the number of vertices) approaches a constant.
Improving Simple Models with Confidence Profiles
Our transfer method involves a theoretically justified weighting of samples during the training of the simple model using confidence scores of these intermediate layers.
Mimic and Classify : A meta-algorithm for Conditional Independence Testing
Given independent samples generated from the joint distribution $p(\mathbf{x},\mathbf{y},\mathbf{z})$, we study the problem of Conditional Independence (CI-Testing), i. e., whether the joint equals the CI distribution $p^{CI}(\mathbf{x},\mathbf{y},\mathbf{z})= p(\mathbf{z}) p(\mathbf{y}|\mathbf{z})p(\mathbf{x}|\mathbf{z})$ or not.
Structure Learning from Time Series with False Discovery Control
Almost all existing Granger causal algorithms condition on a large number of variables (all but two variables) to test for effects between a pair of variables.
Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probes
We propose a novel confidence scoring mechanism for deep neural networks based on a two-model paradigm involving a base model and a meta-model.
Contextual Bandits with Stochastic Experts
We consider the problem of contextual bandits with stochastic experts, which is a variation of the traditional stochastic contextual bandit with experts problem.
Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives
important object pixels in an image) to justify its classification and analogously what should be minimally and necessarily \emph{absent} (viz.
Experimental Design for Learning Causal Graphs with Latent Variables
Next, we propose an algorithm that uses only O(d^2 log n) interventions that can learn the latents between both non-adjacent and adjacent variables.
Model-Powered Conditional Independence Test
We consider the problem of non-parametric Conditional Independence testing (CI testing) for continuous random variables.
A Formal Framework to Characterize Interpretability of Procedures
We provide a novel notion of what it means to be interpretable, looking past the usual association with human understanding.
TIP: Typifying the Interpretability of Procedures
This leads to the insight that the improvement in the target model is not only a function of the oracle model's performance, but also its relative complexity with respect to the target model.
Sparse Quadratic Logistic Regression in Sub-quadratic Time
We consider support recovery in the quadratic logistic regression setting - where the target depends on both p linear terms $x_i$ and up to $p^2$ quadratic terms $x_i x_j$.
Identifying Best Interventions through Online Importance Sampling
Motivated by applications in computational advertising and systems biology, we consider the problem of identifying the best out of several possible soft interventions at a source node $V$ in an acyclic causal directed graph, to maximize the expected value of a target node $Y$ (located downstream of $V$).
Contextual Bandits with Latent Confounders: An NMF Approach
Our algorithm achieves a regret of $\mathcal{O}\left(L\mathrm{poly}(m, \log K) \log T \right)$ at time $T$, as compared to $\mathcal{O}(LK\log T)$ for conventional contextual bandits, assuming a constant gap between the best arm and the rest for each context.
Learning Causal Graphs with Small Interventions
We prove that any deterministic adaptive algorithm needs to be a separating system in order to learn complete graphs in the worst case.
On the Information Theoretic Limits of Learning Ising Models
We provide a general framework for computing lower-bounds on the sample complexity of recovering the underlying graphs of Ising models, given i. i. d samples.
Sparse Polynomial Learning and Graph Sketching
We give an algorithm for exactly reconstructing f given random examples from the uniform distribution on $\{-1, 1\}^n$ that runs in time polynomial in $n$ and $2s$ and succeeds if the function satisfies the unique sign property: there is one output value which corresponds to a unique set of values of the participating parities.
