Boaz Barak
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Boaz Barak has a total of 69 co-authors. Here are the top co-authors by number of shared publications:
- Ankur Moitra
Massachusetts Institute of Technology, Cambridge, USA
3 shared publications - Benjamin L. Edelman
Harvard University
2 shared publications - Chi-Ning Chou
School of Engineering and Applied Sciences Harvard University Cambridge Massachusetts USA
2 shared publications - David Steurer
Cornell University
2 shared publications - Mohammad Mahmoody
University of Virginia
2 shared publications - Pravesh K. Kothari
Princeton University
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 29 February 2024
- Published by American Physical Society (APS) in PRX Quantum
- Vol. 5 (1) , 010334
Limitations of Linear Cross-Entropy as a Measure for Quantum Advantage
Demonstrating quantum advantage requires experimental implementation of a computational task that is hard to achieve using state-of-the-art classical systems. One approach is to perform sampling from a probability distribution associated with a certain class of highly entangled many-body wave functions. It has been suggested that such a quantum advantage can be certified with the linear cross-entropy benchmark (XEB). We critically examine this notion. First, we consider a “benign” setting, where an honest implementation of a noisy quantum circuit is assumed, and characterize the conditions under which the XEB approximates the fidelity of quantum dynamics. Second, we assume an “adversarial” setting, where all possible classical algorithms are considered for comparisons, and show that achieving relatively high XEB values does not imply faithful simulation of quantum dynamics. Specifically, we present an efficient classical algorithm that achieves high XEB values, namely 5–12% of those obtained in the state-of-the-art experiments, within just a few seconds using a single GPU machine. This is made possible by identifying and exploiting several vulnerabilities of the XEB, which allows us to achieve high XEB values without simulating a full quantum circuit. Remarkably, our algorithm features better scaling with the system size than a noisy quantum device for commonly studied random circuit ensembles in various architecture. We quantitatively explain the success of our algorithm and the limitations of the XEB by using a theoretical framework, in which the dynamics of the average XEB and fidelity are mapped to classical statistical mechanics models. Using this framework, we illustrate the relation between the XEB and the fidelity for quantum circuits in various architectures, with different choices of gate sets, and in the presence of noise. Taken together, our results demonstrate that XEB’s utility as a proxy for fidelity hinges on several conditions, which should be independently checked in the benign setting, but cannot be assumed in the general adversarial setting. Therefore, the XEB on its own has a limited utility as a benchmark for quantum advantage. We briefly discuss potential ways to overcome these limitations.
- 29 February 2024
- Published by American Physical Society (APS) in PRX Quantum
- Vol. 5 (1) , 010334
Top Cited PapersOpen AccessLimitations of Linear Cross-Entropy as a Measure for Quantum Advantage
Demonstrating quantum advantage requires experimental implementation of a computational task that is hard to achieve using state-of-the-art classical systems. One approach is to perform sampling from a probability distribution associated with a certain class of highly entangled many-body wave functions. It has been suggested that such a quantum advantage can be certified with the linear cross-entropy benchmark (XEB). We critically examine this notion. First, we consider a “benign” setting, where an honest implementation of a noisy quantum circuit is assumed, and characterize the conditions under which the XEB approximates the fidelity of quantum dynamics. Second, we assume an “adversarial” setting, where all possible classical algorithms are considered for comparisons, and show that achieving relatively high XEB values does not imply faithful simulation of quantum dynamics. Specifically, we present an efficient classical algorithm that achieves high XEB values, namely 5–12% of those obtained in the state-of-the-art experiments, within just a few seconds using a single GPU machine. This is made possible by identifying and exploiting several vulnerabilities of the XEB, which allows us to achieve high XEB values without simulating a full quantum circuit. Remarkably, our algorithm features better scaling with the system size than a noisy quantum device for commonly studied random circuit ensembles in various architecture. We quantitatively explain the success of our algorithm and the limitations of the XEB by using a theoretical framework, in which the dynamics of the average XEB and fidelity are mapped to classical statistical mechanics models. Using this framework, we illustrate the relation between the XEB and the fidelity for quantum circuits in various architectures, with different choices of gate sets, and in the presence of noise. Taken together, our results demonstrate that XEB’s utility as a proxy for fidelity hinges on several conditions, which should be independently checked in the benign setting, but cannot be assumed in the general adversarial setting. Therefore, the XEB on its own has a limited utility as a benchmark for quantum advantage. We briefly discuss potential ways to overcome these limitations.
- Open Access
- 17 October 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-6
Remote inspection of adversary-controlled environments
Remotely monitoring the location and enduring presence of valuable items in adversary-controlled environments presents significant challenges. In this article, we demonstrate a monitoring approach that leverages the gigahertz radio-wave scattering and absorption of a room and its contents, including a set of mirrors with random orientations placed inside, to remotely verify the absence of any disturbance over time. Our technique extends to large physical systems the application of physical unclonable functions for integrity protection. Its main applications are scenarios where parties are mutually distrustful and have privacy and security constraints. Examples range from the verification of nuclear arms-control treaties to the securing of currency, artwork, or data centers.
- 17 October 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-6
Open AccessRemote inspection of adversary-controlled environments
Remotely monitoring the location and enduring presence of valuable items in adversary-controlled environments presents significant challenges. In this article, we demonstrate a monitoring approach that leverages the gigahertz radio-wave scattering and absorption of a room and its contents, including a set of mirrors with random orientations placed inside, to remotely verify the absence of any disturbance over time. Our technique extends to large physical systems the application of physical unclonable functions for integrity protection. Its main applications are scenarios where parties are mutually distrustful and have privacy and security constraints. Examples range from the verification of nuclear arms-control treaties to the securing of currency, artwork, or data centers.
- Open Access
On Provable Copyright Protection for Generative Models
There is a growing concern that learned conditional generative models may output samples that are substantially similar to some copyrighted data $C$ that was in their training set. We give a formal definition of $\textit{near access-freeness (NAF)}$ and prove bounds on the probability that a model satisfying this definition outputs a sample similar to $C$, even if $C$ is included in its training set. Roughly speaking, a generative model $p$ is $\textit{$k$-NAF}$ if for every potentially copyrighted data $C$, the output of $p$ diverges by at most $k$-bits from the output of a model $q$ that $\textit{did not access $C$ at all}$. We also give generative model learning algorithms, which efficiently modify the original generative model learning algorithm in a black box manner, that output generative models with strong bounds on the probability of sampling protected content. Furthermore, we provide promising experiments for both language (transformers) and image (diffusion) generative models, showing minimal degradation in output quality while ensuring strong protections against sampling protected content.Open AccessOn Provable Copyright Protection for Generative Models
There is a growing concern that learned conditional generative models may output samples that are substantially similar to some copyrighted data $C$ that was in their training set. We give a formal definition of $\textit{near access-freeness (NAF)}$ and prove bounds on the probability that a model satisfying this definition outputs a sample similar to $C$, even if $C$ is included in its training set. Roughly speaking, a generative model $p$ is $\textit{$k$-NAF}$ if for every potentially copyrighted data $C$, the output of $p$ diverges by at most $k$-bits from the output of a model $q$ that $\textit{did not access $C$ at all}$. We also give generative model learning algorithms, which efficiently modify the original generative model learning algorithm in a black box manner, that output generative models with strong bounds on the probability of sampling protected content. Furthermore, we provide promising experiments for both language (transformers) and image (diffusion) generative models, showing minimal degradation in output quality while ensuring strong protections against sampling protected content. - Open Access
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
There is mounting evidence of emergent phenomena in the capabilities of deep learning methods as we scale up datasets, model sizes, and training times. While there are some accounts of how these resources modulate statistical capacity, far less is known about their effect on the computational problem of model training. This work conducts such an exploration through the lens of learning a $k$-sparse parity of $n$ bits, a canonical discrete search problem which is statistically easy but computationally hard. Empirically, we find that a variety of neural networks successfully learn sparse parities, with discontinuous phase transitions in the training curves. On small instances, learning abruptly occurs at approximately $n^{O(k)}$ iterations; this nearly matches SQ lower bounds, despite the apparent lack of a sparse prior. Our theoretical analysis shows that these observations are not explained by a Langevin-like mechanism, whereby SGD "stumbles in the dark" until it finds the hidden set of features (a natural algorithm which also runs in $n^{O(k)}$ time). Instead, we show that SGD gradually amplifies the sparse solution via a Fourier gap in the population gradient, making continual progress that is invisible to loss and error metrics.Open AccessHidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
There is mounting evidence of emergent phenomena in the capabilities of deep learning methods as we scale up datasets, model sizes, and training times. While there are some accounts of how these resources modulate statistical capacity, far less is known about their effect on the computational problem of model training. This work conducts such an exploration through the lens of learning a $k$-sparse parity of $n$ bits, a canonical discrete search problem which is statistically easy but computationally hard. Empirically, we find that a variety of neural networks successfully learn sparse parities, with discontinuous phase transitions in the training curves. On small instances, learning abruptly occurs at approximately $n^{O(k)}$ iterations; this nearly matches SQ lower bounds, despite the apparent lack of a sparse prior. Our theoretical analysis shows that these observations are not explained by a Langevin-like mechanism, whereby SGD "stumbles in the dark" until it finds the hidden set of features (a natural algorithm which also runs in $n^{O(k)}$ time). Instead, we show that SGD gradually amplifies the sparse solution via a Fourier gap in the population gradient, making continual progress that is invisible to loss and error metrics. - Top Cited Papers
- 10 June 2022
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 376 (6598) , 1209-1215
Quantum optimization of maximum independent set using Rydberg atom arrays
Realizing quantum speedup for practically relevant, computationally hard problems is a central challenge in quantum information science. Using Rydberg atom arrays with up to 289 qubits in two spatial dimensions, we experimentally investigate quantum algorithms for solving the maximum independent set problem. We use a hardware-efficient encoding associated with Rydberg blockade, realize closed-loop optimization to test several variational algorithms, and subsequently apply them to systematically explore a class of graphs with programmable connectivity. We find that the problem hardness is controlled by the solution degeneracy and number of local minima, and we experimentally benchmark the quantum algorithm’s performance against classical simulated annealing. On the hardest graphs, we observe a superlinear quantum speedup in finding exact solutions in the deep circuit regime and analyze its origins.
- 10 June 2022
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 376 (6598) , 1209-1215
Top Cited PapersQuantum optimization of maximum independent set using Rydberg atom arrays
Realizing quantum speedup for practically relevant, computationally hard problems is a central challenge in quantum information science. Using Rydberg atom arrays with up to 289 qubits in two spatial dimensions, we experimentally investigate quantum algorithms for solving the maximum independent set problem. We use a hardware-efficient encoding associated with Rydberg blockade, realize closed-loop optimization to test several variational algorithms, and subsequently apply them to systematically explore a class of graphs with programmable connectivity. We find that the problem hardness is controlled by the solution degeneracy and number of local minima, and we experimentally benchmark the quantum algorithm’s performance against classical simulated annealing. On the hardest graphs, we observe a superlinear quantum speedup in finding exact solutions in the deep circuit regime and analyze its origins.
- Open Access
- 29 March 2022
- Published by Springer Nature in Mathematical Programming
- Vol. 193 (2) , 513-548
Noisy tensor completion via the sum-of-squares hierarchy
In the noisy tensor completion problem we observementries (whose location is chosen uniformly at random) from an unknown $$n_1 \times n_2 \times n_3$$ tensorT. We assume thatTis entry-wise close to being rankr. Our goal is to fill in its missing entries using as few observations as possible. Let $$n = \max (n_1, n_2, n_3)$$ . We show that if $$m > rsim n^{3/2} r$$ then there is a polynomial time algorithm based on the sixth level of the sum-of-squares hierarchy for completing it. Our estimate agrees with almost all ofT’s entries almost exactly and works even when our observations are corrupted by noise. This is also the first algorithm for tensor completion that works in the overcomplete case when $$r > n$$ , and in fact it works all the way up to $$r = n^{3/2-\epsilon }$$ . Our proofs are short and simple and are based on establishing a new connection between noisy tensor completion (through the language of Rademacher complexity) and the task of refuting random constraint satisfaction problems. This connection seems to have gone unnoticed even in the context of matrix completion. Furthermore, we use this connection to show matching lower bounds. Our main technical result is in characterizing the Rademacher complexity of the sequence of norms that arise in the sum-of-squares relaxations to the tensor nuclear norm. These results point to an interesting new direction: Can we explore computational vs. sample complexity tradeoffs through the sum-of-squares hierarchy?- 29 March 2022
- Published by Springer Nature in Mathematical Programming
- Vol. 193 (2) , 513-548
Open AccessNoisy tensor completion via the sum-of-squares hierarchy
In the noisy tensor completion problem we observementries (whose location is chosen uniformly at random) from an unknown $$n_1 \times n_2 \times n_3$$ tensorT. We assume thatTis entry-wise close to being rankr. Our goal is to fill in its missing entries using as few observations as possible. Let $$n = \max (n_1, n_2, n_3)$$ . We show that if $$m > rsim n^{3/2} r$$ then there is a polynomial time algorithm based on the sixth level of the sum-of-squares hierarchy for completing it. Our estimate agrees with almost all ofT’s entries almost exactly and works even when our observations are corrupted by noise. This is also the first algorithm for tensor completion that works in the overcomplete case when $$r > n$$ , and in fact it works all the way up to $$r = n^{3/2-\epsilon }$$ . Our proofs are short and simple and are based on establishing a new connection between noisy tensor completion (through the language of Rademacher complexity) and the task of refuting random constraint satisfaction problems. This connection seems to have gone unnoticed even in the context of matrix completion. Furthermore, we use this connection to show matching lower bounds. Our main technical result is in characterizing the Rademacher complexity of the sequence of norms that arise in the sum-of-squares relaxations to the tensor nuclear norm. These results point to an interesting new direction: Can we explore computational vs. sample complexity tradeoffs through the sum-of-squares hierarchy? - Open Access
Playing Unique Games on Certified Small-Set Expanders
We give an algorithm for solving unique games (UG) instances whenever low-degree sum-of-squares proofs certify good bounds on the small-set-expansion of the underlying constraint graph via a hypercontractive inequality. Our algorithm is in fact more versatile, and succeeds even when the constraint graph is not a small-set expander as long as the structure of non-expanding small sets is (informally speaking) "characterized" by a low-degree sum-of-squares proof. Our results are obtained by rounding \emph{low-entropy} solutions -- measured via a new global potential function -- to sum-of-squares (SoS) semidefinite programs. This technique adds to the (currently short) list of general tools for analyzing SoS relaxations for \emph{worst-case} optimization problems. As corollaries, we obtain the first polynomial-time algorithms for solving any UG instance where the constraint graph is either the \emph{noisy hypercube}, the \emph{short code} or the \emph{Johnson} graph. The prior best algorithm for such instances was the eigenvalue enumeration algorithm of Arora, Barak, and Steurer (2010) which requires quasi-polynomial time for the noisy hypercube and nearly-exponential time for the short code and Johnson graphs. All of our results achieve an approximation of $1-\epsilon$ vs $\delta$ for UG instances, where $\epsilon>0$ and $\delta > 0$ depend on the expansion parameters of the graph but are independent of the alphabet size.Open AccessPlaying Unique Games on Certified Small-Set Expanders
We give an algorithm for solving unique games (UG) instances whenever low-degree sum-of-squares proofs certify good bounds on the small-set-expansion of the underlying constraint graph via a hypercontractive inequality. Our algorithm is in fact more versatile, and succeeds even when the constraint graph is not a small-set expander as long as the structure of non-expanding small sets is (informally speaking) "characterized" by a low-degree sum-of-squares proof. Our results are obtained by rounding \emph{low-entropy} solutions -- measured via a new global potential function -- to sum-of-squares (SoS) semidefinite programs. This technique adds to the (currently short) list of general tools for analyzing SoS relaxations for \emph{worst-case} optimization problems. As corollaries, we obtain the first polynomial-time algorithms for solving any UG instance where the constraint graph is either the \emph{noisy hypercube}, the \emph{short code} or the \emph{Johnson} graph. The prior best algorithm for such instances was the eigenvalue enumeration algorithm of Arora, Barak, and Steurer (2010) which requires quasi-polynomial time for the noisy hypercube and nearly-exponential time for the short code and Johnson graphs. All of our results achieve an approximation of $1-\epsilon$ vs $\delta$ for UG instances, where $\epsilon>0$ and $\delta > 0$ depend on the expansion parameters of the graph but are independent of the alphabet size. - Open Access
- 4 February 2021
- Published by Springer Nature in Nature Physics
- Vol. 17 (3) , 295-296
Work with what you’ve got
- 4 February 2021
- Published by Springer Nature in Nature Physics
- Vol. 17 (3) , 295-296
Open AccessWork with what you’ve got
- Open Access
Spoofing Linear Cross-Entropy Benchmarking in Shallow Quantum Circuits
The linear cross-entropy benchmark (Linear XEB) has been used as a test for procedures simulating quantum circuits. Given a quantum circuit $C$ with $n$ inputs and outputs and purported simulator whose output is distributed according to a distribution $p$ over $\{0,1\}^n$, the linear XEB fidelity of the simulator is $\mathcal{F}_{C}(p) = 2^n \mathbb{E}_{x \sim p} q_C(x) -1$ where $q_C(x)$ is the probability that $x$ is output from the distribution $C|0^n\rangle$. A trivial simulator (e.g., the uniform distribution) satisfies $\mathcal{F}_C(p)=0$, while Google's noisy quantum simulation of a 53 qubit circuit $C$ achieved a fidelity value of $(2.24\pm0.21)\times10^{-3}$ (Arute et. al., Nature'19). In this work we give a classical randomized algorithm that for a given circuit $C$ of depth $d$ with Haar random 2-qubit gates achieves in expectation a fidelity value of $\Omega(\tfrac{n}{L} \cdot 15^{-d})$ in running time $\textsf{poly}(n,2^L)$. Here $L$ is the size of the \emph{light cone} of $C$: the maximum number of input bits that each output bit depends on. In particular, we obtain a polynomial-time algorithm that achieves large fidelity of $\omega(1)$ for depth $O(\sqrt{\log n})$ two-dimensional circuits. To our knowledge, this is the first such result for two dimensional circuits of super-constant depth. Our results can be considered as an evidence that fooling the linear XEB test might be easier than achieving a full simulation of the quantum circuit.Open AccessSpoofing Linear Cross-Entropy Benchmarking in Shallow Quantum Circuits
The linear cross-entropy benchmark (Linear XEB) has been used as a test for procedures simulating quantum circuits. Given a quantum circuit $C$ with $n$ inputs and outputs and purported simulator whose output is distributed according to a distribution $p$ over $\{0,1\}^n$, the linear XEB fidelity of the simulator is $\mathcal{F}_{C}(p) = 2^n \mathbb{E}_{x \sim p} q_C(x) -1$ where $q_C(x)$ is the probability that $x$ is output from the distribution $C|0^n\rangle$. A trivial simulator (e.g., the uniform distribution) satisfies $\mathcal{F}_C(p)=0$, while Google's noisy quantum simulation of a 53 qubit circuit $C$ achieved a fidelity value of $(2.24\pm0.21)\times10^{-3}$ (Arute et. al., Nature'19). In this work we give a classical randomized algorithm that for a given circuit $C$ of depth $d$ with Haar random 2-qubit gates achieves in expectation a fidelity value of $\Omega(\tfrac{n}{L} \cdot 15^{-d})$ in running time $\textsf{poly}(n,2^L)$. Here $L$ is the size of the \emph{light cone} of $C$: the maximum number of input bits that each output bit depends on. In particular, we obtain a polynomial-time algorithm that achieves large fidelity of $\omega(1)$ for depth $O(\sqrt{\log n})$ two-dimensional circuits. To our knowledge, this is the first such result for two dimensional circuits of super-constant depth. Our results can be considered as an evidence that fooling the linear XEB test might be easier than achieving a full simulation of the quantum circuit. - Open Access
SGD on Neural Networks Learns Functions of Increasing Complexity
We perform an experimental study of the dynamics of Stochastic Gradient Descent (SGD) in learning deep neural networks for several real and synthetic classification tasks. We show that in the initial epochs, almost all of the performance improvement of the classifier obtained by SGD can be explained by a linear classifier. More generally, we give evidence for the hypothesis that, as iterations progress, SGD learns functions of increasing complexity. This hypothesis can be helpful in explaining why SGD-learned classifiers tend to generalize well even in the over-parameterized regime. We also show that the linear classifier learned in the initial stages is "retained" throughout the execution even if training is continued to the point of zero training error, and complement this with a theoretical result in a simplified model. Key to our work is a new measure of how well one classifier explains the performance of another, based on conditional mutual information.
Open AccessSGD on Neural Networks Learns Functions of Increasing Complexity
We perform an experimental study of the dynamics of Stochastic Gradient Descent (SGD) in learning deep neural networks for several real and synthetic classification tasks. We show that in the initial epochs, almost all of the performance improvement of the classifier obtained by SGD can be explained by a linear classifier. More generally, we give evidence for the hypothesis that, as iterations progress, SGD learns functions of increasing complexity. This hypothesis can be helpful in explaining why SGD-learned classifiers tend to generalize well even in the over-parameterized regime. We also show that the linear classifier learned in the initial stages is "retained" throughout the execution even if training is continued to the point of zero training error, and complement this with a theoretical result in a simplified model. Key to our work is a new measure of how well one classifier explains the performance of another, based on conditional mutual information.