Rati Gelashvili

Zeyuan Allen-Zhu, Rati Gelashvili, Ilya Razenshteyn

The Restricted Isometry Property (RIP) is a fundamental property of a matrix which enables sparse recovery. Informally, an $m \times n$ matrix satisfies RIP of order $k$ for the $\ell_p$ norm, if $\|Ax\|_p \approx \|x\|_p$ for every vector $x$ with at most $k$ non-zero coordinates. For every $1 \leq p < \infty$ we obtain almost tight bounds on the minimum number of rows $m$ necessary for the RIP property to hold. Prior to this work, only the cases $p = 1$, $1 + 1 / \log k$, and $2$ were studied. Interestingly, our results show that the case $p = 2$ is a "singularity" point: the optimal number of rows $m$ is $\widetildeΘ(k^{p})$ for all $p\in [1,\infty)\setminus \{2\}$, as opposed to $\widetildeΘ(k)$ for $k=2$. We also obtain almost tight bounds for the column sparsity of RIP matrices and discuss implications of our results for the Stable Sparse Recovery problem.

Rati Gelashvili, Lefteris Kokoris-Kogias, Alberto Sonnino et al.

Existing committee-based Byzantine state machine replication (SMR) protocols, typically deployed in production blockchains, face a clear trade-off: (1) they either achieve linear communication cost in the happy path, but sacrifice liveness during periods of asynchrony, or (2) they are robust (progress with probability one) but pay quadratic communication cost. We believe this trade-off is unwarranted since existing linear protocols still have asymptotic quadratic cost in the worst case. We design Ditto, a Byzantine SMR protocol that enjoys the best of both worlds: optimal communication on and off the happy path (linear and quadratic, respectively) and progress guarantee under asynchrony and DDoS attacks. We achieve this by replacing the view-synchronization of partially synchronous protocols with an asynchronous fallback mechanism at no extra asymptotic cost. Specifically, we start from HotStuff, a state-of-the-art linear protocol, and gradually build Ditto. As a separate contribution and an intermediate step, we design a 2-chain version of HotStuff, Jolteon, which leverages a quadratic view-change mechanism to reduce the latency of the standard 3-chain HotStuff. We implement and experimentally evaluate all our systems. Notably, Jolteon's commit latency outperforms HotStuff by 200-300ms with varying system size. Additionally, Ditto adapts to the network and provides better performance than Jolteon under faulty conditions and better performance than VABA (a state-of-the-art asynchronous protocol) under faultless conditions. This proves our case that breaking the robustness-efficiency trade-off is in the realm of practicality.

Rati Gelashvili, Lefteris Kokoris-Kogias, Alexander Spiegelman et al.

The popularity of permissioned blockchain systems demands BFT SMR protocols that are efficient under good network conditions (synchrony) and robust under bad network conditions (asynchrony). The state-of-the-art partially synchronous BFT SMR protocols provide optimal linear communication cost per decision under synchrony and good leaders, but lose liveness under asynchrony. On the other hand, the state-of-the-art asynchronous BFT SMR protocols are live even under asynchrony, but always pay quadratic cost even under synchrony. In this paper, we propose a BFT SMR protocol that achieves the best of both worlds -- optimal linear cost per decision under good networks and leaders, optimal quadratic cost per decision under bad networks, and remains always live.

Rati Gelashvili, Nir Shavit, Aleksandar Zlateski

Fast convolutions via transforms, either Winograd or FFT, had emerged as a preferred way of performing the computation of convolutional layers, as it greatly reduces the number of required operations. Recent work shows that, for many layer structures, a well--designed implementation of fast convolutions can greatly utilize modern CPUs, significantly reducing the compute time. However, the generous amount of shared L3 cache present on modern CPUs is often neglected, and the algorithms are optimized solely for the private L2 cache. In this paper we propose an efficient `L3 Fusion` algorithm that is specifically designed for CPUs with significant amount of shared L3 cache. Using the hierarchical roofline model, we show that in many cases, especially for layers with fewer channels, the `L3 fused` approach can greatly outperform standard 3 stage one provided by big vendors such as Intel. We validate our theoretical findings, by benchmarking our `L3 fused` implementation against publicly available state of the art.