Phenomenon of stochastic separability was revealed and used in machine learning to correct errors Artificial Intelligence (AI) systems analyze AI instabilities. In high-dimensional datasets under broad assumptions each point can be separated from the rest set by simple robust Fisher’s discriminant (is Fisher separable). Errors or clusters data. The ability an system also opens up possibility at...

We consider an example network where we compute the bounds on cell loss rates. The stochastic bounds for these loss rates using simple arguments lead to models easier to solve. We proved, using stochastic orders, that the loss rates of these easier models are really the bounds of our original model. For ill-balanced configurations these models give good estimates of loss rates.

We develop a class of lower bounds on the expectation of a convex function. The bounds utilize the first two moments of the underlying random variable, whose support is contained in a bounded interval or hyperrectangle. Our bounds have applications to stochastic programs whose random parameters are known only through limitedmoment information. Computational results are presented for two-stage s...

In Stochastic Control Theory Course project, I have studied the LQG approach in Gaussian Broadcast Channels with feedback and Gaussian Multiple Access Channels (MAC) with Feedback. Control theoretic approach in communication channels is studied by many authors. Some of those are by G. Kramer [1] which was presented in a more simple form in [2]. Similar work was also done by N. Elia [3]. I have ...

We study upper and lower bounds on the sample-complexity of learning nearoptimal behaviour in finite-state discounted Markov Decision Processes (mdps). We prove a new bound for a modified version of Upper Confidence Reinforcement Learning (ucrl) with only cubic dependence on the horizon. The bound is unimprovable in all parameters except the size of the state/action space, where it depends line...