Chirag Gupta

Chirag Gupta, Aaditya Ramdas

We study the problem of making calibrated probabilistic forecasts for a binary sequence generated by an adversarial nature. Following the seminal paper of Foster and Vohra (1998), nature is often modeled as an adaptive adversary who sees all activity of the forecaster except the randomization that the forecaster may deploy. A number of papers have proposed randomized forecasting strategies that achieve an $ε$-calibration error rate of $O(1/\sqrt{T})$, which we prove is tight in general. On the other hand, it is well known that it is not possible to be calibrated without randomization, or if nature also sees the forecaster's randomization; in both cases the calibration error could be $Ω(1)$. Inspired by the equally seminal works on the "power of two choices" and imprecise probability theory, we study a small variant of the standard online calibration problem. The adversary gives the forecaster the option of making two nearby probabilistic forecasts, or equivalently an interval forecast of small width, and the endpoint closest to the revealed outcome is used to judge calibration. This power of two choices, or imprecise forecast, accords the forecaster with significant power -- we show that a faster $ε$-calibration rate of $O(1/T)$ can be achieved even without deploying any randomization.

Youngseog Chung, Aaron Rumack, Chirag Gupta

In a sequential regression setting, a decision-maker may be primarily concerned with whether the future observation will increase or decrease compared to the current one, rather than the actual value of the future observation. In this context, we introduce the notion of parity calibration, which captures the goal of calibrated forecasting for the increase-decrease (or "parity") event in a timeseries. Parity probabilities can be extracted from a forecasted distribution for the output, but we show that such a strategy leads to theoretical unpredictability and poor practical performance. We then observe that although the original task was regression, parity calibration can be expressed as binary calibration. Drawing on this connection, we use an online binary calibration method to achieve parity calibration. We demonstrate the effectiveness of our approach on real-world case studies in epidemiology, weather forecasting, and model-based control in nuclear fusion.

Chirag Gupta

Man-Computer Symbiosis (MCS) was originally envisioned by the famous computer pioneer J.C.R. Licklider in 1960, as a logical evolution of the then inchoate relationship between computer and humans. In his paper, Licklider provided a set of criteria by which to judge if a Man-Computer System is a symbiotic one, and also provided some predictions about such systems in the near and far future. Since then, innovations in computer networks and the invention of the Internet were major developments towards that end. However, with most systems based on conventional logical algorithms, many aspects of Licklider's MCS remained unfulfilled. This paper explores the extent to which modern machine learning systems in general, and deep learning ones in particular best exemplify MCS systems, and why they are the prime contenders to achieve a true Man-Computer Symbiosis as described by Licklider in his original paper in the future. The case for deep learning is built by illustrating each point of the original criteria as well as the criteria laid by subsequent research into MCS systems, with specific examples and applications provided to strengthen the arguments. The efficacy of deep neural networks in achieving Artificial General Intelligence, which would be the perfect version of an MCS system is also explored.

Chirag Gupta, Chikita Nangia, Chetan Kumar

With the advancements in high volume, low precision computational technology and applied research on cognitive artificially intelligent heuristic systems, machine learning solutions through neural networks with real-time learning has seen an immense interest in the research community as well the industry. This paper involves research, development and experimental analysis of a neural network implemented on a robot with an arm through which evolves to learn to walk in a straight line or as required. The neural network learns using the algorithms of Gradient Descent and Backpropagation. Both the implementation and training of the neural network is done locally on the robot on a raspberry pi 3 so that its learning process is completely independent. The neural network is first tested on a custom simulator developed on MATLAB and then implemented on the raspberry computer. Data at each generation of the evolving network is stored, and analysis both mathematical and graphical is done on the data. Impact of factors like the learning rate and error tolerance on the learning process and final output is analyzed.