Publications de Volkan Cevher | EPFL Graph Search

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

In this paper, the problem of multiple speaker localization via speech separation based on model-based sparse recovery is studies. We compare and contrast computational sparse optimization methods incorporating harmonicity and block structures as well as a ...

Polynomial Networks (PNs) have demonstrated promising performance on face and image recognition recently. However, robustness of PNs is unclear and thus obtaining certificates becomes imperative for enabling their adoption in real-world applications. Exist ...

We consider the homogeneous and the non-homogeneous convex relaxations for combinatorial penalty functions defined on support sets. Our study identifies key differences in the tightness of the resulting relaxations through the notion of the lower combinato ...

We cast the under-determined convolutive speech separation as sparse approximation of the spatial spectra of the mixing sources. In this framework we compare and contrast the major practical algorithms for structured sparse recovery of speech signal. Speci ...

In this paper, we aim to build the global convergence theory of encoder-only shallow Transformers under a realistic setting from the perspective of architectures, initialization, and scaling under a finite width regime. The difficulty lies in how to tackle ...

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adv ...

In this paper, we study the information-theoretic limits of community detection in the symmetric two-community stochastic block model, with intra-community and inter-community edge probabilities

\frac{a}{n}

and

\frac{b}{n}

respectively. We consider the ...

We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative sequence of demonst ...

Next generation invasive neural interfaces require fully implantable wireless systems that can record from a large number of channels simultaneously. However, transferring the recorded data from the implant to an external receiver emerges as a significant ...

We consider the problem of finding a saddle point for the convex-concave objective

\min_x \max_y f(x) + \langle Ax, y\rangle - g^*(y)

, where

f

is a convex function with locally Lipschitz gradient and

g

is convex and possibly non-smooth. We propose an ...

This letter presents an energy-and-area-efficient ac-coupled front-end for the multichannel recording of wideband neural signals. The proposed unit conditions local held and action potentials using an inverter-based capacitively coupled low-noise amplifier ...

In this paper, we extend the generalized approximate message passing (G-AMP) approach, originally proposed for high-dimensional generalized-linear regression in the context of compressive sensing, to the generalized-bilinear case. In Part I of this two-par ...

This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayesoptimal test error for classification while obtaining (nearly) zero-trai ...

We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the under-parameterized setting, width has a negative effect while it improves ...

This paper develops a methodology for regret minimization with stochastic first-order oracle feedback in online, constrained, non-smooth, non-convex problems. In this setting, the minimization of external regret is beyond reach for first-order methods, and ...

We propose a stochastic gradient framework for solving stochastic composite convex optimization problems with (possibly) infinite number of linear inclusion constraints that need to be satisfied almost surely. We use smoothing and homotopy techniques to ha ...

Modern deep neural networks exhibit heterogeneity across numerous layers of various types such as residuals, multi-head attention, etc., due to varying structures (dimensions, activation functions, etc.), distinct representation characteristics, which impa ...

In this paper, we consider the problem of Gaussian process (GP) optimization with an added robustness requirement: The returned point may be perturbed by an adversary, and we require the function value to remain as high as possible even after this perturba ...

Most learning methods with rank or sparsity constraints use convex relaxations, which lead to optimization with the nuclear norm or the`1-norm. However, several important learning applications cannot benet from this approach as they feature these convex no ...

Machine learning promises to accelerate materials discovery by allowing computational efficient property predictions from a small number of reference calculations. As a result, the literature spent a considerable effort in designing representations that ca ...

Volkan Cevher

Chattez avec Graph Search

Model-based Sparse Component Analysis for Reverberant Speech Localization

Sound and Complete Verification of Polynomial Networks

Combinatorial Penalties: Which structures are preserved by convex relaxations?

Computational Methods For Structured Sparse Component Analysis of Convolutive Speech Mixtures

On the Convergence of Encoder-only Shallow Transformers

Revisiting Character-level Adversarial Attacks for Language Models

Partial Recovery Bounds for the Sparse Stochastic Block Model

Interactive Teaching Algorithms for Inverse Reinforcement Learning

A 16-Channel Neural Recording System-on-Chip With CHT Feature Extraction Processor in 65-nm CMOS

A first-order primal-dual method with adaptivity to local smoothness

An AC-Coupled Wideband Neural Recording Front-End With Sub-1 mm2×fJ/conv-step Efficiency and 0.97 NEF

Bilinear Generalized Approximate Message Passing—Part II: Applications

Benign Overfitting in Deep Neural Networks under Lazy Training

Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)

Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach

Almost surely constrained convex optimization

Layer-wise Quantization for Quantized Optimistic Dual Averaging

Adversarially Robust Optimization with Gaussian Processes

Sparse projections onto the simplex

Chemical machine learning with kernels: The key impact of loss functions