Search Results for author:
Found 11 papers, 1 papers with code
On Bits and Bandits: Quantifying the Regret-Information Trade-off
We study the trade-off between the information an agent accumulates and the regret it suffers.
A representation-learning game for classes of prediction tasks
We propose a game-based formulation for learning dimensionality-reducing representations of feature vectors, when only a prior knowledge on future prediction tasks is available.
Statistical curriculum learning: An elimination algorithm achieving an oracle risk
In the single source case, we propose an elimination learning method, whose risk matches that of a strong-oracle learner.
Characterization of the Distortion-Perception Tradeoff for Finite Channels with Arbitrary Metrics
We provide a structural characterization of the DP tradeoff, where the DP function is piecewise linear in the perception index.
The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting -- An Analytical Model
Previous works have analyzed separately how forgetting is affected by either task similarity or overparameterization.
Maximal-Capacity Discrete Memoryless Channel Identification
Based on this capacity estimator, a gap-elimination algorithm termed BestChanID is proposed, which is oblivious to the capacity-achieving input distribution and is guaranteed to output the DMC with the largest capacity, with a desired confidence.
How do Minimum-Norm Shallow Denoisers Look in Function Space?
Neural network (NN) denoisers are an essential building block in many common tasks, ranging from image reconstruction to image generation.
Multi-Armed Bandits with Self-Information Rewards
Additionally, under the assumption that the \textit{exact} alphabet size is unknown, and instead the player only knows a loose upper bound on it, a UCB-based algorithm is proposed, in which the player aims to reduce the regret caused by the unknown alphabet size in a finite time regime.
Mean Estimation in High-Dimensional Binary Markov Gaussian Mixture Models
In this model, an estimator observes $n$ samples of a $d$-dimensional parameter vector $\theta_{*}\in\mathbb{R}^{d}$, multiplied by a random sign $ S_i $ ($1\le i\le n$), and corrupted by isotropic standard Gaussian noise.
Robust Linear Regression for General Feature Distribution
In this work we go beyond these assumptions and investigate robust regression under a more general set of assumptions: $\textbf{(i)}$ we allow the covariance matrix to be either positive definite or positive semi definite, $\textbf{(ii)}$ we do not necessarily assume that the features are centered, $\textbf{(iii)}$ we make no further assumption beyond boundedness (sub-Gaussianity) of features and measurement noise.
The EM Algorithm is Adaptively-Optimal for Unbalanced Symmetric Gaussian Mixtures
For the empirical iteration based on $n$ samples, we show that when initialized at $\theta_{0}=0$, the EM algorithm adaptively achieves the minimax error rate $\tilde{O}\Big(\min\Big\{\frac{1}{(1-2\delta_{*})}\sqrt{\frac{d}{n}},\frac{1}{\|\theta_{*}\|}\sqrt{\frac{d}{n}},\left(\frac{d}{n}\right)^{1/4}\Big\}\Big)$ in no more than $O\Big(\frac{1}{\|\theta_{*}\|(1-2\delta_{*})}\Big)$ iterations (with high probability).
