Understanding the Effect of Bias in Deep Anomaly Detection

Anomaly detection presents a unique challenge in machine learning, due to the scarcity of labeled anomaly data. Recent work attempts to mitigate such problems by augmenting training of deep anomaly detection models with additional labeled anomaly samples. However, the labeled data often does not align with the target distribution and introduces harmful bias to the trained model. In this paper, we aim to understand the effect of a biased anomaly set on anomaly detection. Concretely, we view anomaly detection as a supervised learning task where the objective is to optimize the recall at a given false positive rate. We formally study the relative scoring bias of an anomaly detector, defined as the difference in performance with respect to a baseline anomaly detector. We establish the first finite sample rates for estimating the relative scoring bias for deep anomaly detection, and empirically validate our theoretical results on both synthetic and real-world datasets. We also provide an extensive empirical study on how a biased training anomaly set affects the anomaly score function and therefore the detection performance on different anomaly classes. Our study demonstrates scenarios in which the biased anomaly set can be useful or problematic, and provides a solid benchmark for future research.

Generating Continuous Motion and Force Plans in Real-Time for Legged Mobile Manipulation

Manipulators can be added to legged robots, allowing them to interact with and change their environment. Legged mobile manipulation planners must consider how contact forces generated by these manipulators affect the system. Current planning strategies either treat these forces as immutable during planning or are unable to optimize over these contact forces while operating in real-time. This paper presents the Stability and Task Oriented Receding-Horizon Motion and Manipulation Autonomous Planner (STORMMAP) that is able to generate continuous plans for the robot's motion and manipulation force trajectories that ensure dynamic feasibility and stability of the platform, and incentivizes accomplishing manipulation and motion tasks specified by a user. STORMMAP uses a nonlinear optimization problem to compute these plans and is able to run in real-time by assuming contact locations are given a-priori, either by a user or an external algorithm. A variety of simulated experiments on a quadruped with a manipulator mounted to its torso demonstrate the versatility of STORMMAP. In contrast to existing state of the art methods, the approach described in this paper generates continuous plans in under ten milliseconds, an order of magnitude faster than previous strategies.

Towards an Interpretable Data-driven Trigger System for High-throughput Physics Facilities

Data-intensive science is increasingly reliant on real-time processing capabilities and machine learning workflows, in order to filter and analyze the extreme volumes of data being collected. This is especially true at the energy and intensity frontiers of particle physics where bandwidths of raw data can exceed 100 Tb/s of heterogeneous, high-dimensional data sourced from hundreds of millions of individual sensors. In this paper, we introduce a new data-driven approach for designing and optimizing high-throughput data filtering and trigger systems such as those in use at physics facilities like the Large Hadron Collider (LHC). Concretely, our goal is to design a data-driven filtering system with a minimal run-time cost for determining which data event to keep, while preserving (and potentially improving upon) the distribution of the output as generated by the hand-designed trigger system. We introduce key insights from interpretable predictive modeling and cost-sensitive learning in order to account for non-local inefficiencies in the current paradigm and construct a cost-effective data filtering and trigger model that does not compromise physics coverage.

Minimax Estimation of Linear Functions of Eigenvectors in the Face of Small Eigen-Gaps

Eigenvector perturbation analysis plays a vital role in various statistical data science applications. A large body of prior works, however, focused on establishing $\ell_{2}$ eigenvector perturbation bounds, which are often highly inadequate in addressing tasks that rely on fine-grained behavior of an eigenvector. This paper makes progress on this by studying the perturbation of linear functions of an unknown eigenvector. Focusing on two fundamental problems -- matrix denoising and principal component analysis -- in the presence of Gaussian noise, we develop a suite of statistical theory that characterizes the perturbation of arbitrary linear functions of an unknown eigenvector. In order to mitigate a non-negligible bias issue inherent to the natural "plug-in" estimator, we develop de-biased estimators that (1) achieve minimax lower bounds for a family of scenarios (modulo some logarithmic factor), and (2) can be computed in a data-driven manner without sample splitting. Noteworthily, the proposed estimators are nearly minimax optimal even when the associated eigen-gap is substantially smaller than what is required in prior theory.

Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis

Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. When it comes to the synchronous setting (such that independent samples for all state-action pairs are drawn from a generative model in each iteration), substantial progress has been made recently towards understanding the sample efficiency of Q-learning. Take a $\gamma$-discounted infinite-horizon MDP with state space $\mathcal{S}$ and action space $\mathcal{A}$: to yield an entrywise $\varepsilon$-accurate estimate of the optimal Q-function, state-of-the-art theory for Q-learning proves that a sample size on the order of $\frac{|\mathcal{S}||\mathcal{A}|}{(1-\gamma)^5\varepsilon^{2}}$ is sufficient, which, however, fails to match with the existing minimax lower bound. This gives rise to natural questions: what is the sharp sample complexity of Q-learning? Is Q-learning provably sub-optimal? In this work, we settle these questions by (1) demonstrating that the sample complexity of Q-learning is at most on the order of $\frac{|\mathcal{S}||\mathcal{A}|}{(1-\gamma)^4\varepsilon^2}$ (up to some log factor) for any $0<\varepsilon <1$, and (2) developing a matching lower bound to confirm the sharpness of our result. Our findings unveil both the effectiveness and limitation of Q-learning: its sample complexity matches that of speedy Q-learning without requiring extra computation and storage, albeit still being considerably higher than the minimax lower bound.

Softmax Policy Gradient Methods Can Take Exponential Time to Converge

The softmax policy gradient (PG) method, which performs gradient ascent under softmax policy parameterization, is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. For $\gamma$-discounted infinite-horizon tabular Markov decision processes (MDPs), remarkable progress has recently been achieved towards establishing global convergence of softmax PG methods in finding a near-optimal policy. However, prior results fall short of delineating clear dependencies of convergence rates on salient parameters such as the cardinality of the state space $\mathcal{S}$ and the effective horizon $\frac{1}{1-\gamma}$, both of which could be excessively large. In this paper, we deliver a pessimistic message regarding the iteration complexity of softmax PG methods, despite assuming access to exact gradient computation. Specifically, we demonstrate that softmax PG methods can take exponential time -- in terms of $|\mathcal{S}|$ and $\frac{1}{1-\gamma}$ -- to converge, even in the presence of a benign policy initialization and an initial state distribution amenable to exploration. This is accomplished by characterizing the algorithmic dynamics over a carefully-constructed MDP containing only three actions. Our exponential lower bound hints at the necessity of carefully adjusting update rules or enforcing proper regularization in accelerating PG methods.

Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning

Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. When it comes to the synchronous setting (such that independent samples for all state-action pairs are drawn from a generative model in each iteration), substantial progress has been made recently towards understanding the sample efficiency of Q-learning. To yield an entrywise $\varepsilon$-accurate estimate of the optimal Q-function, state-of-the-art theory requires at least an order of $\frac{|\mathcal{S}||\mathcal{A}|}{(1-\gamma)^5\varepsilon^{2}}$ samples for a $\gamma$-discounted infinite-horizon MDP with state space $\mathcal{S}$ and action space $\mathcal{A}$. In this work, we sharpen the sample complexity of synchronous Q-learning to an order of $\frac{|\mathcal{S}||\mathcal{A}|}{(1-\gamma)^4\varepsilon^2}$ (up to some logarithmic factor) for any $0<\varepsilon <1$, leading to an order-wise improvement in terms of the effective horizon $\frac{1}{1-\gamma}$. Analogous results are derived for finite-horizon MDPs as well. Our finding unveils the effectiveness of vanilla Q-learning, which matches that of speedy Q-learning without requiring extra computation and storage. A key ingredient of our analysis lies in the establishment of novel error decompositions and recursions, which might shed light on how to analyze finite-sample performance of other Q-learning variants.

Spectral Methods for Data Science: A Statistical Perspective

Spectral methods have emerged as a simple yet surprisingly effective approach for extracting information from massive, noisy and incomplete data. In a nutshell, spectral methods refer to a collection of algorithms built upon the eigenvalues (resp. singular values) and eigenvectors (resp. singular vectors) of some properly designed matrices constructed from data. A diverse array of applications have been found in machine learning, data science, and signal processing. Due to their simplicity and effectiveness, spectral methods are not only used as a stand-alone estimator, but also frequently employed to initialize other more sophisticated algorithms to improve performance. While the studies of spectral methods can be traced back to classical matrix perturbation theory and methods of moments, the past decade has witnessed tremendous theoretical advances in demystifying their efficacy through the lens of statistical modeling, with the aid of non-asymptotic random matrix theory. This monograph aims to present a systematic, comprehensive, yet accessible introduction to spectral methods from a modern statistical perspective, highlighting their algorithmic implications in diverse large-scale applications. In particular, our exposition gravitates around several central questions that span various applications: how to characterize the sample efficiency of spectral methods in reaching a target level of statistical accuracy, and how to assess their stability in the face of random noise, missing data, and adversarial corruptions? In addition to conventional $\ell_2$ perturbation analysis, we present a systematic $\ell_{\infty}$ and $\ell_{2,\infty}$ perturbation theory for eigenspace and singular subspaces, which has only recently become available owing to a powerful "leave-one-out" analysis framework.

The Teaching Dimension of Kernel Perceptron

Algorithmic machine teaching has been studied under the linear setting where exact teaching is possible. However, little is known for teaching nonlinear learners. Here, we establish the sample complexity of teaching, aka teaching dimension, for kernelized perceptrons for different families of feature maps. As a warm-up, we show that the teaching complexity is $\Theta(d)$ for the exact teaching of linear perceptrons in $\mathbb{R}^d$, and $\Theta(d^k)$ for kernel perceptron with a polynomial kernel of order $k$. Furthermore, under certain smooth assumptions on the data distribution, we establish a rigorous bound on the complexity for approximately teaching a Gaussian kernel perceptron. We provide numerical examples of the optimal (approximate) teaching set under several canonical settings for linear, polynomial and Gaussian kernel perceptrons.

Learning Time Varying Risk Preferences from Investment Portfolios using Inverse Optimization with Applications on Mutual Funds

The fundamental principle in Modern Portfolio Theory (MPT) is based on the quantification of the portfolio's risk related to performance. Although MPT has made huge impacts on the investment world and prompted the success and prevalence of passive investing, it still has shortcomings in real-world applications. One of the main challenges is that the level of risk an investor can endure, known as \emph{risk-preference}, is a subjective choice that is tightly related to psychology and behavioral science in decision making. This paper presents a novel approach of measuring risk preference from existing portfolios using inverse optimization on the mean-variance portfolio allocation framework. Our approach allows the learner to continuously estimate real-time risk preferences using concurrent observed portfolios and market price data. We demonstrate our methods on real market data that consists of 20 years of asset pricing and 10 years of mutual fund portfolio holdings. Moreover, the quantified risk preference parameters are validated with two well-known risk measurements currently applied in the field. The proposed methods could lead to practical and fruitful innovations in automated/personalized portfolio management, such as Robo-advising, to augment financial advisors' decision intelligence in a long-term investment horizon.