While the comparison table in this article applies to a specific problem in FinTech, the conclusions are consistent with findings in other frameworks. There is no single method that outperforms all the other ones, for obvious reasons. To be the global winner means winning on all potential datasets. The immense majority of datasets are pure noise, for which performance is meaningless, and the winner randomly changes from one dataset to another. Yet, in real-life applications, each dataset comes with patterns or meaningful signal.

With everything going computerized and digital, the amount of data generated by us is humongous. Organizations collectively spend billions of dollars to just store and analyze this data. They make efforts to drive valuable business insights from this data using data mining. Data Mining is the process of discovering hidden patterns in a pile of big data. Business executives use these emerging patterns to make informed business strategy decisions.

Previous analysis of regularized functional linear regression in a reproducing kernel Hilbert space (RKHS) typically requires the target function to be contained in this kernel space. This paper studies the convergence performance of divide-and-conquer estimators in the scenario that the target function does not necessarily reside in the underlying RKHS. As a decomposition-based scalable approach, the divide-and-conquer estimators of functional linear regression can substantially reduce the algorithmic complexities in time and memory. We develop an integral operator approach to establish sharp finite sample upper bounds for prediction with divide-and-conquer estimators under various regularity conditions of explanatory variables and target function. We also prove the asymptotic optimality of the derived rates by building the mini-max lower bounds. Finally, we consider the convergence of noiseless estimators and show that the rates can be arbitrarily fast under mild conditions.

In this video, you will learn from basics to advanced machine learning concepts from Great Learning's top faculties, including professor Mukesh Rao, Bharani Akella & many other leading industry experts. If you are an enthusiast who wants to start with machine learning from scratch, this machine learning beginner video is the best to start with. Agenda: • Python for Machine Learning • Role of Statistics in Machine Learning • Introduction to Machine Learning and its types • How does a Machine learning model learn? Topics Covered: 00:01:09 – What Is Machine learning?

We propose \textbf{JAWS}, a series of wrapper methods for distribution-free uncertainty quantification tasks under covariate shift, centered on the core method \textbf{JAW}, the \textbf{JA}ckknife+ \textbf{W}eighted with data-dependent likelihood-ratio weights. JAWS also includes computationally efficient \textbf{A}pproximations of JAW using higher-order influence functions: \textbf{JAWA}. Theoretically, we show that JAW relaxes the jackknife+'s assumption of data exchangeability to achieve the same finite-sample coverage guarantee even under covariate shift. JAWA further approaches the JAW guarantee in the limit of the sample size or the influence function order under common regularity assumptions. Moreover, we propose a general approach to repurposing predictive interval-generating methods and their guarantees to the reverse task: estimating the probability that a prediction is erroneous, based on user-specified error criteria such as a safe or acceptable tolerance threshold around the true label. We then propose \textbf{JAW-E} and \textbf{JAWA-E} as the repurposed proposed methods for this \textbf{E}rror assessment task. Practically, JAWS outperform state-of-the-art predictive inference baselines in a variety of biased real world data sets for interval-generation and error-assessment predictive uncertainty auditing tasks.

Leveraging transfer learning has recently been shown to be an effective strategy for training large models with Differential Privacy (DP). Moreover, somewhat surprisingly, recent works have found that privately training just the last layer of a pre-trained model provides the best utility with DP. While past studies largely rely on algorithms like DP-SGD for training large models, in the specific case of privately learning from features, we observe that computational burden is low enough to allow for more sophisticated optimization schemes, including second-order methods. To that end, we systematically explore the effect of design parameters such as loss function and optimization algorithm. We find that, while commonly used logistic regression performs better than linear regression in the non-private setting, the situation is reversed in the private setting. We find that linear regression is much more effective than logistic regression from both privacy and computational aspects, especially at stricter epsilon values ($\epsilon < 1$). On the optimization side, we also explore using Newton's method, and find that second-order information is quite helpful even with privacy, although the benefit significantly diminishes with stricter privacy guarantees. While both methods use second-order information, least squares is effective at lower epsilons while Newton's method is effective at larger epsilon values. To combine the benefits of both, we propose a novel algorithm called DP-FC, which leverages feature covariance instead of the Hessian of the logistic regression loss and performs well across all $\epsilon$ values we tried. With this, we obtain new SOTA results on ImageNet-1k, CIFAR-100 and CIFAR-10 across all values of $\epsilon$ typically considered. Most remarkably, on ImageNet-1K, we obtain top-1 accuracy of 88\% under (8, $8 * 10^{-7}$)-DP and 84.3\% under (0.1, $8 * 10^{-7}$)-DP.

We begin the study of list-decodable linear regression using batches. In this setting only an $\alpha \in (0,1]$ fraction of the batches are genuine. Each genuine batch contains $\ge n$ i.i.d. samples from a common unknown distribution and the remaining batches may contain arbitrary or even adversarial samples. We derive a polynomial time algorithm that for any $n\ge \tilde \Omega(1/\alpha)$ returns a list of size $\mathcal O(1/\alpha^2)$ such that one of the items in the list is close to the true regression parameter. The algorithm requires only $\tilde{\mathcal{O}}(d/\alpha^2)$ genuine batches and works under fairly general assumptions on the distribution. The results demonstrate the utility of batch structure, which allows for the first polynomial time algorithm for list-decodable regression, which may be impossible for the non-batch setting, as suggested by a recent SQ lower bound \cite{diakonikolas2021statistical} for the non-batch setting.

Traffic simulation is a great tool to demonstrate complex traffic structures which can be extremely useful for the planning, development, and management of road traffic networks. Current traffic simulators offer limited features when it comes to interactive and adaptive traffic modeling. This paper presents RegTraffic, a novel interactive traffic simulator that integrates dynamic regression-based spatiotemporal traffic analysis to predict congestion of intercorrelated road segments. The simulator models traffic congestion of road segments depending on neighboring road links and temporal features of the dynamic traffic flow. The simulator provides a user-friendly web interface to select road segments of interest, receive user-defined traffic parameters, and visualize the traffic for the flow of correlated road links based on the user inputs and the underlying correlation of these road links. Performance evaluation shows that RegTraffic can effectively predict traffic congestion with a Mean Squared Error of 1.3 Km/h and a Root Mean Squared Error of 1.71 Km/h. RegTraffic can effectively simulate the results and provide visualization on interactive geographical maps.

Predicting the accuracy of candidate neural architectures is an important capability of NAS-based solutions. When a candidate architecture has properties that are similar to other known architectures, the prediction task is rather straightforward using off-the-shelf regression algorithms. However, when a candidate architecture lies outside of the known space of architectures, a regression model has to perform extrapolated predictions, which is not only a challenging task, but also technically impossible using the most popular regression algorithm families, which are based on decision trees. In this work, we are trying to address two problems. The first one is improving regression accuracy using feature selection, whereas the other one is the evaluation of regression algorithms on extrapolating accuracy prediction tasks. We extend the NAAP-440 dataset with new tabular features and introduce NAAP-440e, which we use for evaluation. We observe a dramatic improvement from the old baseline, namely, the new baseline requires 3x shorter training processes of candidate architectures, while maintaining the same mean-absolute-error and achieving almost 2x fewer monotonicity violations, compared to the old baseline's best reported performance. The extended dataset and code used in the study have been made public in the NAAP-440 repository.

Big streams of Earth images from satellites or other platforms (e.g., drones and mobile phones) are becoming increasingly available at low or no cost and with enhanced spatial and temporal resolution. This thesis recognizes the unprecedented opportunities offered by the high quality and open access Earth observation data of our times and introduces novel machine learning and big data methods to properly exploit them towards developing applications for sustainable and resilient agriculture. The thesis addresses three distinct thematic areas, i.e., the monitoring of the Common Agricultural Policy (CAP), the monitoring of food security and applications for smart and resilient agriculture. The methodological innovations of the developments related to the three thematic areas address the following issues: i) the processing of big Earth Observation (EO) data, ii) the scarcity of annotated data for machine learning model training and iii) the gap between machine learning outputs and actionable advice. This thesis demonstrated how big data technologies such as data cubes, distributed learning, linked open data and semantic enrichment can be used to exploit the data deluge and extract knowledge to address real user needs. Furthermore, this thesis argues for the importance of semi-supervised and unsupervised machine learning models that circumvent the ever-present challenge of scarce annotations and thus allow for model generalization in space and time. Specifically, it is shown how merely few ground truth data are needed to generate high quality crop type maps and crop phenology estimations. Finally, this thesis argues there is considerable distance in value between model inferences and decision making in real-world scenarios and thereby showcases the power of causal and interpretable machine learning in bridging this gap.