You need to log in to edit.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

no code implementations • ICML 2020 • Fariborz Salehi, Ehsan Abbasi, Babak Hassibi

The performance of hard-margin SVM has been recently analyzed in~\cite{montanari2019generalization, deng2019model}.

no code implementations • 18 Feb 2023 • Danil Akhtiamov, Babak Hassibi

This is best understood in linear over-parametrized models where it has been shown that the celebrated stochastic gradient descent (SGD) algorithm finds an interpolating solution that is closest in Euclidean distance to the initial weight vector.

no code implementations • 13 Feb 2023 • David Bosch, Ashkan Panahi, Babak Hassibi

We provide exact asymptotic expressions for the performance of regression by an $L-$layer deep random feature (RF) model, where the input is mapped through multiple random embedding and non-linear activation functions.

no code implementations • 27 Oct 2022 • Taylan Kargin, Fariborz Salehi, Babak Hassibi

The stochastic mirror descent (SMD) algorithm is a general class of training algorithms, which includes the celebrated stochastic gradient descent (SGD), as a special case.

no code implementations • 17 Jun 2022 • Taylan Kargin, Sahin Lale, Kamyar Azizzadenesheli, Anima Anandkumar, Babak Hassibi

By carefully prescribing an early exploration strategy and a policy update rule, we show that TS achieves order-optimal regret in adaptive control of multidimensional stabilizable LQRs.

no code implementations • 3 Jun 2022 • Oron Sabag, Sahin Lale, Babak Hassibi

The key techniques that underpin our explicit solution is a reduction of the control problem to a Nehari problem, along with a novel factorization of the clairvoyant controller's cost.

no code implementations • 22 Feb 2022 • Navid Azizan, Sahin Lale, Babak Hassibi

RMD starts with a standard cost which is the sum of the training loss and a convex regularizer of the weights.

no code implementations • 24 Oct 2021 • Gautam Goel, Babak Hassibi

A natural goal when designing online learning algorithms for non-stationary environments is to bound the regret of the algorithm in terms of the temporal variation of the input sequence.

no code implementations • 5 Oct 2021 • Farshad Lahouti, Victoria Kostina, Babak Hassibi

Empirical studies suggest that each triplet query takes an expert at most 50\% more time compared with a pairwise query, indicating the effectiveness of the proposed $k$-ary query schemes.

no code implementations • 26 Aug 2021 • Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar

Using these guarantees, we design adaptive control algorithms for unknown ARX systems with arbitrary strongly convex or convex quadratic regulating costs.

no code implementations • 28 Jul 2021 • Gautam Goel, Babak Hassibi

We consider control from the perspective of competitive analysis.

no code implementations • 22 Jun 2021 • Gautam Goel, Babak Hassibi

We consider estimation and control in linear time-varying dynamical systems from the perspective of regret minimization.

no code implementations • 4 May 2021 • Oron Sabag, Gautam Goel, Sahin Lale, Babak Hassibi

Motivated by learning theory, as a criterion for controller design we focus on regret, defined as the difference between the LQR cost of a causal controller (that has only access to past and current disturbances) and the LQR cost of a clairvoyant one (that has also access to future disturbances).

no code implementations • 28 Mar 2021 • Mohammed H. AlSharif, Ahmed Douik, Mohanad Ahmed, Tareq Y. Al-Naffouri, Babak Hassibi

This paper reports the design of a high-accuracy spatial location estimation method using ultrasound waves by exploiting the fixed geometry of the transmitters.

1 code implementation • 25 Jan 2021 • Oron Sabag, Babak Hassibi

For the important case of signals that can be described with a time-invariant state-space, we provide an explicit construction for the regret optimal filter in the estimation (causal) and the prediction (strictly-causal) regimes.

no code implementations • 8 Dec 2020 • Sahin Lale, Oguzhan Teke, Babak Hassibi, Anima Anandkumar

In this model, each state variable is updated randomly and asynchronously with some probability according to the underlying system dynamics.

no code implementations • 24 Nov 2020 • Gautam Goel, Babak Hassibi

We consider measurement-feedback control in linear dynamical systems from the perspective of regret minimization.

no code implementations • 29 Oct 2020 • Fariborz Salehi, Ehsan Abbasi, Babak Hassibi

We also provide a detailed study for three special cases: ($1$) $\ell_2$-GMM that is the max-margin classifier, ($2$) $\ell_1$-GMM which encourages sparsity, and ($3$) $\ell_{\infty}$-GMM which is often used when the parameter vector has binary entries.

no code implementations • 29 Oct 2020 • Fariborz Salehi, Babak Hassibi

To this end, in this paper we consider the problem of binary classification with adversarial perturbations.

no code implementations • 20 Oct 2020 • Gautam Goel, Babak Hassibi

We consider control in linear time-varying dynamical systems from the perspective of regret minimization.

no code implementations • 23 Jul 2020 • Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar

In this work, we study model-based reinforcement learning (RL) in unknown stabilizable linear dynamical systems.

Model-based Reinforcement Learning
reinforcement-learning
**+1**

no code implementations • NeurIPS 2020 • Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar

We study the problem of system identification and adaptive control in partially observable linear dynamical systems.

no code implementations • 12 Mar 2020 • Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar

We study the problem of adaptive control in partially observable linear quadratic Gaussian control systems, where the model dynamics are unknown a priori.

no code implementations • 7 Feb 2020 • Gautam Goel, Babak Hassibi

We also show that cost of the optimal offline linear policy converges to the cost of the optimal online policy as the time horizon grows large, and consequently the optimal offline linear policy incurs linear regret relative to the optimal offline policy, even in the optimistic setting where the noise is drawn i. i. d from a known distribution.

no code implementations • 6 Feb 2020 • Chung-Yi Lin, Victoria Kostina, Babak Hassibi

We introduce the principle we call Differential Quantization (DQ) that prescribes compensating the past quantization errors to direct the descent trajectory of a quantized algorithm towards that of its unquantized counterpart.

no code implementations • 31 Jan 2020 • Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar

We propose a novel way to decompose the regret and provide an end-to-end sublinear regret upper bound for partially observable linear quadratic control.

no code implementations • 25 Sep 2019 • Navid Azizan, Sahin Lale, Babak Hassibi

On the theory side, we show that in the overparameterized nonlinear setting, if the initialization is close enough to the manifold of global optima, SMD with sufficiently small step size converges to a global minimum that is approximately the closest global minimum in Bregman divergence, thus attaining approximate implicit regularization.

no code implementations • NeurIPS 2019 • Fariborz Salehi, Ehsan Abbasi, Babak Hassibi

In both cases, we obtain explicit expressions for various performance metrics and can find the values of the regularizer parameter that optimizes the desired performance.

1 code implementation • 10 Jun 2019 • Navid Azizan, Sahin Lale, Babak Hassibi

Most modern learning problems are highly overparameterized, meaning that there are many more parameters than the number of training data points, and as a result, the training loss may have infinitely many global minima (parameter vectors that perfectly interpolate the training data).

no code implementations • 3 Apr 2019 • Navid Azizan, Babak Hassibi

Stochastic mirror descent (SMD) is a fairly new family of algorithms that has recently found a wide range of applications in optimization, machine learning, and control.

no code implementations • 28 Jan 2019 • Sahin Lale, Kamyar Azizzadenesheli, Anima Anandkumar, Babak Hassibi

We modify the image classification task into the SLB setting and empirically show that, when a pre-trained DNN provides the high dimensional feature representations, deploying PSLB results in significant reduction of regret and faster convergence to an accurate model compared to state-of-art algorithm.

no code implementations • NeurIPS 2018 • Fariborz Salehi, Ehsan Abbasi, Babak Hassibi

The problem of estimating an unknown signal, $\mathbf x_0\in \mathbb R^n$, from a vector $\mathbf y\in \mathbb R^m$ consisting of $m$ magnitude-only measurements of the form $y_i=|\mathbf a_i\mathbf x_0|$, where $\mathbf a_i$'s are the rows of a known measurement matrix $\mathbf A$ is a classical problem known as phase retrieval.

no code implementations • ICML 2018 • Ahmed Douik, Babak Hassibi

This paper develops a Riemannian optimization framework for solving optimization problems on the set of symmetric positive semidefinite stochastic matrices.

no code implementations • ICLR 2019 • Navid Azizan, Babak Hassibi

In an attempt to shed some light on why this is the case, we revisit some minimax properties of stochastic gradient descent (SGD) for the square loss of linear models---originally developed in the 1990's---and extend them to general stochastic mirror descent (SMD) algorithms for general loss functions and nonlinear models.

no code implementations • NeurIPS 2017 • Ashkan Panahi, Babak Hassibi

Precise expressions for the asymptotic performance of LASSO have been obtained for a number of different cases, in particular when the elements of the dictionary matrix are sampled independently from a Gaussian distribution.

no code implementations • 4 Aug 2017 • Navid Azizan-Ruhi, Farshad Lahouti, Salman Avestimehr, Babak Hassibi

In this paper, we consider a common scenario in which a taskmaster intends to solve a large-scale system of linear equations by distributing subsets of the equations among a number of computing machines/cores.

no code implementations • 28 Jan 2017 • Murat Kocaoglu, Alexandros G. Dimakis, Sriram Vishwanath, Babak Hassibi

This framework requires the solution of a minimum entropy coupling problem: Given marginal distributions of m discrete random variables, each on n states, find the joint distribution with minimum entropy, that respects the given marginals.

no code implementations • NeurIPS 2016 • Ramya Korlakai Vinayak, Babak Hassibi

When a generative model for the data is available (and we consider a few of these) we determine the cost of a query by its entropy; when such models do not exist we use the average response time per query of the workers as a surrogate for the cost.

1 code implementation • 12 Nov 2016 • Murat Kocaoglu, Alexandros G. Dimakis, Sriram Vishwanath, Babak Hassibi

We show that the problem of finding the exogenous variable with minimum entropy is equivalent to the problem of finding minimum joint entropy given $n$ marginal distributions, also known as minimum entropy coupling problem.

no code implementations • NeurIPS 2016 • Farshad Lahouti, Babak Hassibi

The results are established by a joint source channel (de)coding scheme, which represent the query scheme and inference, over parallel noisy channels, which model workers with imperfect skill levels.

no code implementations • NeurIPS 2015 • Christos Thrampoulidis, Ehsan Abbasi, Babak Hassibi

In this work, we considerably strengthen these results by obtaining explicit expressions for $\|\hat x-\mu x_0\|_2$, for the regularized Generalized-LASSO, that are asymptotically precise when $m$ and $n$ grow large.

no code implementations • NeurIPS 2014 • Ramya Korlakai Vinayak, Samet Oymak, Babak Hassibi

We consider the problem of finding clusters in an unweighted graph, when the graph is partially observed.

no code implementations • 4 Nov 2013 • Samet Oymak, Christos Thrampoulidis, Babak Hassibi

The first LASSO estimator assumes a-priori knowledge of $f(x_0)$ and is given by $\arg\min_{x}\{{\|y-Ax\|_2}~\text{subject to}~f(x)\leq f(x_0)\}$.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.