Search Results for author:
Found 57 papers, 3 papers with code
Current Implicit Policies May Not Eradicate COVID-19
Successful predictive modeling of epidemics requires an understanding of the implicit feedback control strategies which are implemented by populations to modulate the spread of contagion.
Counterfactual inference for sequential experimental design
Second, for a generic non-parametric latent factor model, we establish that the estimate for the missing outcome of any unit at time $\mathbf{T}$ satisfies a central limit theorem as $\mathbf{T} \to \infty$, under suitable regularity conditions.
Unifying Epidemic Models with Mixtures
The model represents time series of cases and fatalities as a mixture of Gaussian curves, providing a flexible function class to learn from data compared to traditional mechanistic models.
Federated Optimization of Smooth Loss Functions
Under some assumptions on the loss function, e. g., strong convexity in parameter, $\eta$-H\"older smoothness in data, etc., we prove that the federated oracle complexity of FedLRGD scales like $\phi m(p/\epsilon)^{\Theta(d/\eta)}$ and that of FedAve scales like $\phi m(p/\epsilon)^{3/4}$ (neglecting sub-dominant factors), where $\phi\gg 1$ is a "communication-to-computation ratio," $p$ is the parameter dimension, and $d$ is the data dimension.
CausalSim: Unbiased Trace-Driven Network Simulation
Through an adversarial neural network training technique that exploits distributional invariances that are present in training data coming from an RCT, CausalSim enables a novel tensor completion method despite the sparsity of observations.
Time varying regression with hidden linear dynamics
We revisit a model for time-varying linear regression that assumes the unknown parameters evolve according to a linear dynamical system.
Change Point Detection via Multivariate Singular Spectrum Analysis
The change point in such a setting corresponds to a change in the underlying spatio-temporal model.
A Computationally Efficient Method for Learning Exponential Family Distributions
In this work, we propose a computationally efficient estimator that is consistent as well as asymptotically normal under mild conditions.
Causal Matrix Completion
In particular, we establish entry-wise, i. e., max-norm, finite-sample consistency and asymptotic normality results for matrix completion with MNAR data.
Quantifying Variational Approximation for the Log-Partition Function
Specifically, we argue that (a variant of) TRW produces an estimate that is within factor $\frac{1}{\sqrt{\kappa(G)}}$ of the true log-partition function for any discrete pairwise graphical model over graph $G$, where $\kappa(G) \in (0, 1]$ captures how far $G$ is from tree structure with $\kappa(G) = 1$ for trees and $2/N$ for the complete graph over $N$ vertices.
PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators
We consider offline reinforcement learning (RL) with heterogeneous agents under severe data scarcity, i. e., we only observe a single historical trajectory for every agent under an unknown, potentially sub-optimal policy.
Regret, stability & fairness in matching markets with bandit learners
In this work, we study how competition affects the long-term outcomes of individuals as they learn.
Estimation of Skill Distribution from a Tournament
In this paper, we study the problem of learning the skill distribution of a population of agents from observations of pairwise games in a tournament.
Gradient-Based Empirical Risk Minimization using Local Polynomial Regression
In contrast, we demonstrate that when the loss function is smooth in the data, we can learn the oracle at every iteration and beat the oracle complexities of both GD and SGD in important regimes.
On Learning Continuous Pairwise Markov Random Fields
We consider learning a sparse pairwise Markov Random Field (MRF) with continuous-valued variables from i. i. d samples.
On Principal Component Regression in a High-Dimensional Error-in-Variables Setting
We analyze the classical method of principal component regression (PCR) in a high-dimensional error-in-variables setting.
On Multivariate Singular Spectrum Analysis and its Variants
We introduce and analyze a simpler, practically useful variant of multivariate singular spectrum analysis (mSSA), a known time series method to impute (or de-noise) and forecast a multivariate time series.
Estimation of Skill Distributions
In this paper, we study the problem of learning the skill distribution of a population of agents from observations of pairwise games in a tournament.
Synthetic Interventions
Theoretically, under a novel tensor factor model across units, measurements, and interventions, we formally establish an identification result for each of these $N \times D$ causal parameters and establish finite-sample consistency and asymptotic normality of our estimator.
Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation
As our key contribution, we develop a simple, iterative learning algorithm that finds $\epsilon$-optimal $Q$-function with sample complexity of $\widetilde{O}(\frac{1}{\epsilon^{\max(d_1, d_2)+2}})$ when the optimal $Q$-function has low rank $r$ and the discounting factor $\gamma$ is below a certain threshold.
Stable Reinforcement Learning with Unbounded State Space
As a proof of concept, we propose an RL policy using Sparse-Sampling-based Monte Carlo Oracle and argue that it satisfies the stability property as long as the system dynamics under the optimal policy respects a Lyapunov function.
Two Burning Questions on COVID-19: Did shutting down the economy help? Can we (partially) reopen the economy without risking the second wave?
In essence, the method leverages information from different interventions that have already been enacted across the world and fits it to a policy maker's setting of interest, e. g., to estimate the effect of mobility-restricting interventions on the U. S., we use daily death data from countries that enforced severe mobility restrictions to create a "synthetic low mobility U. S." and predict the counterfactual trajectory of the U. S. if it had indeed applied a similar intervention.
On Reinforcement Learning for Turn-based Zero-sum Markov Games
For a concrete instance of EIS where random policy is used for "exploration", Monte-Carlo Tree Search is used for "policy improvement" and Nearest Neighbors is used for "supervised learning", we establish that this method finds an $\varepsilon$-approximate value function of Nash equilibrium in $\widetilde{O}(\varepsilon^{-(d+4)})$ steps when the underlying state-space of the game is continuous and $d$-dimensional.
Short and Wide Network Paths
We show this notion of pipelined network flow is optimized using network paths that are both short and wide, and develop efficient algorithms to compute such paths for given pairs of nodes and for all-pairs.
Robust Max Entrywise Error Bounds for Sparse Tensor Estimation via Similarity Based Collaborative Filtering
We prove that the algorithm recovers a low rank tensor with maximum entry-wise error (MEE) and mean-squared-error (MSE) decaying to $0$ as long as each entry is observed independently with probability $p = \Omega(n^{-3/2 + \kappa})$ for any arbitrarily small $\kappa > 0$.
Understanding & Generalizing AlphaGo Zero
AlphaGo Zero (AGZ) introduced a new {\em tabula rasa} reinforcement learning algorithm that has achieved superhuman performance in the games of Go, Chess, and Shogi with no prior knowledge other than the rules of the game.
tspDB: Time Series Predict DB
Computationally, tspDB is 59-62x and 94-95x faster compared to LSTM and DeepAR in terms of median ML model training time and prediction query latency, respectively.
On Robustness of Principal Component Regression
As an important contribution to the Synthetic Control literature, we establish that an (approximate) linear synthetic control exists in the setting of a generalized factor model; traditionally, the existence of a synthetic control needs to be assumed to exist as an axiom.
Non-Asymptotic Analysis of Monte Carlo Tree Search
In effect, we establish that to learn an $\varepsilon$ approximation of the value function with respect to $\ell_\infty$ norm, MCTS combined with nearest neighbor requires a sample size scaling as $\widetilde{O}\big(\varepsilon^{-(d+4)}\big)$, where $d$ is the dimension of the state space.
Learning RUMs: Reducing Mixture to Single Component via PCA
Despite the success of RUMs in various domains and the versatility of mixture RUMs to capture the heterogeneity in preferences, there has been only limited progress in learning a mixture of RUMs from partial data such as pairwise comparisons.
Regret vs. Bandwidth Trade-off for Recommendation Systems
We consider recommendation systems that need to operate under wireless bandwidth constraints, measured as number of broadcast transmissions, and demonstrate a (tight for some instances) tradeoff between regret and bandwidth for two scenarios: the case of multi-armed bandit with context, and the case where there is a latent structure in the message space that we can exploit to reduce the learning phase.
Model Agnostic Time Series Analysis via Matrix Estimation
In effect, this generalizes the widely used Singular Spectrum Analysis (SSA) in time series literature, and allows us to establish a rigorous link between time series analysis and matrix estimation.
Q-learning with Nearest Neighbors
In particular, for MDPs with a $d$-dimensional state space and the discounted factor $\gamma \in (0, 1)$, given an arbitrary sample path with "covering time" $ L $, we establish that the algorithm is guaranteed to output an $\varepsilon$-accurate estimate of the optimal Q-function using $\tilde{O}\big(L/(\varepsilon^3(1-\gamma)^7)\big)$ samples.
Thy Friend is My Friend: Iterative Collaborative Filtering for Sparse Matrix Estimation
We show that the mean squared error (MSE) of our estimator converges to $0$ at the rate of $O(d^2 (pn)^{-2/5})$ as long as $\omega(d^5 n)$ random entries from a total of $n^2$ entries of $Y$ are observed (uniformly sampled), $\E[Y]$ has rank $d$, and the entries of $Y$ have bounded support.
Robust Synthetic Control
Our experiments, using both real-world and synthetic datasets, demonstrate that our robust generalization yields an improvement over the classical synthetic control method.
Reducing Crowdsourcing to Graphon Estimation, Statistically
Inferring the correct answers to binary tasks based on multiple noisy answers in an unsupervised manner has emerged as the canonical question for micro-task crowdsourcing or more generally aggregating opinions.
Blind Regression: Nonparametric Regression for Latent Variable Models via Collaborative Filtering
In contrast with classical regression, the features $x = (x_1(u), x_2(i))$ are not observed, making it challenging to apply standard regression methods to predict the unobserved ratings.
A Latent Source Model for Patch-Based Image Segmentation
Despite the popularity and empirical success of patch-based nearest-neighbor and weighted majority voting approaches to medical image segmentation, there has been no theoretical development on when, why, and how well these nonparametric methods work.
Regret Guarantees for Item-Item Collaborative Filtering
There is much empirical evidence that item-item collaborative filtering works well in practice.
Structure learning of antiferromagnetic Ising models
In this paper we investigate the computational complexity of learning the graph structure underlying a discrete undirected graphical model from i. i. d.
Learning Mixed Multinomial Logit Model from Ordinal Data
In case of single MNL models (no mixture), computationally and statistically tractable learning from pair-wise comparisons is feasible.
A Latent Source Model for Online Collaborative Filtering
Despite the prevalence of collaborative filtering in recommendation systems, there has been little theoretical development on why and how well it works, especially in the "online" setting, where items are recommended to users over time.
Learning graphical models from the Glauber dynamics
In this paper we consider the problem of learning undirected graphical models from data generated according to the Glauber dynamics.
Bayesian regression and Bitcoin
In this paper, we discuss the method of Bayesian regression and its efficacy for predicting price variation of Bitcoin, a recently popularized virtual, cryptographic currency.
Statistical inference with probabilistic graphical models
These are notes from the lecture of Devavrat Shah given at the autumn school "Statistical Physics, Optimization, Inference, and Message-Passing Algorithms", that took place in Les Houches, France from Monday September 30th, 2013, till Friday October 11th, 2013.
Hardness of parameter estimation in graphical models
Our proof gives a polynomial time reduction from approximating the partition function of the hard-core model, known to be hard, to learning approximate parameters.
Computing the Stationary Distribution Locally
In this paper, we provide a novel algorithm that answers whether a chosen state in a MC has stationary probability larger than some $\Delta \in (0, 1)$.
Partition-Merge: Distributed Inference and Modularity Optimization
This paper presents a novel meta algorithm, Partition-Merge (PM), which takes existing centralized algorithms for graph computation and makes them distributed and faster.
A Latent Source Model for Nonparametric Time Series Classification
Our guiding hypothesis is that in many applications, such as forecasting which topics will become trends on Twitter, there aren't actually that many prototypical time series to begin with, relative to the number of time series we have access to, e. g., topics become trends on Twitter only in a few distinct manners whereas we can collect massive amounts of Twitter data.
Iterative ranking from pair-wise comparisons
In most settings, in addition to obtaining ranking, finding ‘scores’ for each object (e. g. player’s rating) is of interest to understanding the intensity of the preferences.
Rank Centrality: Ranking from Pair-wise Comparisons
To study the efficacy of the algorithm, we consider the popular Bradley-Terry-Luce (BTL) model (equivalent to the Multinomial Logit (MNL) for pair-wise comparisons) in which each object has an associated score which determines the probabilistic outcomes of pair-wise comparisons between objects.
Iterative Learning for Reliable Crowdsourcing Systems
Crowdsourcing systems, in which tasks are electronically distributed to numerous ``information piece-workers'', have emerged as an effective paradigm for human-powered solving of large scale problems in domains such as image classification, data entry, optical character recognition, recommendation, and proofreading.
Budget-Optimal Task Allocation for Reliable Crowdsourcing Systems
Further, we compare our approach with a more general class of algorithms which can dynamically assign tasks.
Leaders, Followers, and Community Detection
For a large number of popular social networks, it recovers communities with a much higher F1 score than other popular algorithms.
A Data-Driven Approach to Modeling Choice
We visit the following fundamental problem: For a `generic model of consumer choice (namely, distributions over preference lists) and a limited amount of data on how consumers actually make decisions (such as marginal preference information), how may one predict revenues from offering a particular assortment of choices?
Local Rules for Global MAP: When Do They Work ?
We consider the question of computing Maximum A Posteriori (MAP) assignment in an arbitrary pair-wise Markov Random Field (MRF).
Local Algorithms for Approximate Inference in Minor-Excluded Graphs
We present a new local approximation algorithm for computing MAP and log-partition function for arbitrary exponential family distribution represented by a finite-valued pair-wise Markov random field (MRF), say G. Our algorithm is based on decomposing G into appropriately chosen small components; computing estimates locally in each of these components and then producing a good global solution.
