arXiv subjects

Massimo Franceschetti

Publications and source records attributed to Massimo Franceschetti.

At least 37 records · Page 2Linked to original sources

arXiv2021

Sequential Choice Bandits with Feedback for Personalizing users' experience

In this work, we study sequential choice bandits with feedback. We propose bandit algorithms for a platform that personalizes users' experience to maximize its rewards. For each action directed to a given user, the platform is given a positive reward, which is a non-decreasing function of the action, if this action is below the user's threshold. Users are equipped with a patience budget, and actions that are above the threshold decrease the user's patience. When all patience is lost, the user abandons the platform. The platform attempts to learn the thresholds of the users in order to maximize its rewards, based on two different feedback models describing the information pattern available to the platform at each action. We define a notion of regret by determining the best action to be taken when the platform knows that the user's threshold is in a given interval. We then propose bandit algorithms for the two feedback models and show that upper and lower bounds on the regret are of the order of $\tilde{O}(N^{2/3})$ and $\tildeΩ(N^{2/3})$, respectively, where $N$ is the total number of users. Finally, we show that the waiting time of any user before receiving a personalized experience is uniform in $N$.

stat.ML↗

arXiv2020

Distributed Chernoff Test: Optimal decision systems over networks

We study "active" decision making over sensor networks where the sensors' sequential probing actions are actively chosen by continuously learning from past observations. We consider two network settings: with and without central coordination. In the first case, the network nodes interact with each other through a central entity, which plays the role of a fusion center. In the second case, the network nodes interact in a fully distributed fashion. In both of these scenarios, we propose sequential and adaptive hypothesis tests extending the classic Chernoff test. We compare the performance of the proposed tests to the optimal sequential test. In the presence of a fusion center, our test achieves the same asymptotic optimality of the Chernoff test, minimizing the risk, expressed by the expected cost required to reach a decision plus the expected cost of making a wrong decision, when the observation cost per unit time tends to zero. The test is also asymptotically optimal in the higher moments of the time required to reach a decision. Additionally, the test is parsimonious in terms of communications, and the expected number of channel uses per network node tends to a small constant. In the distributed setup, our test achieves the same asymptotic optimality of Chernoff's test, up to a multiplicative constant in terms of both risk and the higher moments of the decision time. Additionally, the test is parsimonious in terms of communications in comparison to state-of-the-art schemes proposed in the literature. The analysis of these tests is also extended to account for message quantization and communication over channels with random erasures.

stat.ME↗

arXiv2020

Non-Stochastic Information Theory

In an effort to develop the foundations for a non-stochastic theory of information, the notion of $δ$-mutual information between uncertain variables is introduced as a generalization of Nair's non-stochastic information functional. Several properties of this new quantity are illustrated, and used to prove a channel coding theorem in a non-stochastic setting. Namely, it is shown that the largest $δ$-mutual information between received and transmitted codewords over $ε$-noise channels equals the $(ε, δ)$-capacity. This notion of capacity generalizes the Kolmogorov $ε$-capacity to packing sets of overlap at most $δ$, and is a variation of a previous definition proposed by one of the authors. Results are then extended to more general noise models, and to non-stochastic, memoryless, stationary channels. Finally, sufficient conditions are established for the factorization of the $δ$-mutual information and to obtain a single letter capacity expression. Compared to previous non-stochastic approaches, the presented theory admits the possibility of decoding errors as in Shannon's probabilistic setting, while retaining a worst-case, non-stochastic character.

cs.IT↗

arXiv2020

Evolution and Limiting Configuration of a Long-Range Schelling-Type Spin System

We consider a long-range interacting particle system in which binary particles -- whose initial states are chosen uniformly at random -- are located at the nodes of a flat torus $(\mathbb{Z}/h\mathbb{Z})^2$. Each node of the torus is connected to all the nodes located in an $l_\infty$-ball of radius $w$ in the toroidal space centered at itself and we assume that $h$ is exponentially larger than $w^2$. Based on the states of the neighboring particles and on the value of a common intolerance threshold $τ$, every particle is labeled "stable," or "unstable." Every unstable particle that can become stable by flipping its state is labeled "p-stable." Finally, unstable particles that remained p-stable for a random, independent and identically distributed waiting time, flip their state and become stable. When the waiting times have an exponential distribution and $τ\le 1/2$, this model is equivalent to a Schelling model of self-organized segregation in an open system, a zero-temperature Ising model with Glauber dynamics, or an Asynchronous Cellular Automaton (ACA) with extended Moore neighborhoods. We first prove a shape theorem for the spreading of the "affected" nodes of a given state -- namely nodes on which a particle of a given state would be p-stable. As $w \rightarrow \infty$, this spreading starts with high probability (w.h.p.) from any $l_\infty$-ball in the torus having radius $w/2$ and containing only affected nodes, and continues for a time that is at least exponential in the cardinalilty of the neighborhood of interaction $N = (2w+1)^2$. Second, we show that when the process reaches a limiting configuration and no more state changes occur, for all ${τ\in (τ^*,1-τ^*) \setminus \{1/2\}}$ where ${τ^* \approx 0.488}$, w.h.p. any particle is contained in a large "monochromatic ball" of cardinality exponential in $N$.

math.PR↗

arXiv2020

Exploiting timing information in event-triggered stabilization of linear systems with disturbances

In the same way that subsequent pauses in spoken language are used to convey information, it is also possible to transmit information in communication networks not only by message content, but also with its timing. This paper presents an event-triggering strategy that utilizes timing information by transmitting in a state-dependent fashion. We consider the stabilization of a continuous-time, time-invariant, linear plant over a digital communication channel with bounded delay and subject to bounded plant disturbances and establish two main results. On the one hand, we design an encoding-decoding scheme that guarantees a sufficient information transmission rate for stabilization. On the other hand, we determine a lower bound on the information transmission rate necessary for stabilization by any control policy.

eess.SY↗

arXiv2020

Learning-based attacks in cyber-physical systems

We introduce the problem of learning-based attacks in a simple abstraction of cyber-physical systems---the case of a discrete-time, linear, time-invariant plant that may be subject to an attack that overrides the sensor readings and the controller actions. The attacker attempts to learn the dynamics of the plant and subsequently override the controller's actuation signal, to destroy the plant without being detected. The attacker can feed fictitious sensor readings to the controller using its estimate of the plant dynamics and mimic the legitimate plant operation. The controller, on the other hand, is constantly on the lookout for an attack; once the controller detects an attack, it immediately shuts the plant off. In the case of scalar plants, we derive an upper bound on the attacker's deception probability for any measurable control policy when the attacker uses an arbitrary learning algorithm to estimate the system dynamics. We then derive lower bounds for the attacker's deception probability for both scalar and vector plants by assuming a specific authentication test that inspects the empirical variance of the system disturbance. We also show how the controller can improve the security of the system by superimposing a carefully crafted privacy-enhancing signal on top of the "nominal control policy." Finally, for nonlinear scalar dynamics that belong to the Reproducing Kernel Hilbert Space (RKHS), we investigate the performance of attacks based on nonlinear Gaussian-processes (GP) learning algorithms.

eess.SY↗

arXiv2020

Probabilistic Safety Constraints for Learned High Relative Degree System Dynamics

This paper focuses on learning a model of system dynamics online while satisfying safety constraints.Our motivation is to avoid offline system identification or hand-specified dynamics models and allowa system to safely and autonomously estimate and adapt its own model during online operation.Given streaming observations of the system state, we use Bayesian learning to obtain a distributionover the system dynamics. In turn, the distribution is used to optimize the system behavior andensure safety with high probability, by specifying a chance constraint over a control barrier function.

cs.RO↗

arXiv2019

Theory and implementation of event-triggered stabilization over digital channels

In the context of event-triggered control, the timing of the triggering events carries information about the state of the system that can be used for stabilization. At each triggering event, not only can information be transmitted by the message content (data payload) but also by its timing. We demonstrate this in the context of stabilization of a laboratory-scale inverted pendulum around its equilibrium point over a digital communication channel with bounded unknown delay. Our event-triggering control strategy encodes timing information by transmitting in a state-dependent fashion and can achieve stabilization using a data payload transmission rate lower than what the data-rate theorem prescribes for classical periodic control policies that do not exploit timing information. Through experimental results, we show that as the delay in the communication channel increases, a higher data payload transmission rate is required to fulfill the proposed event-triggering policy requirements. This confirms the theoretical intuition that a larger delay brings a larger uncertainty about the value of the state at the controller, as less timing information is carried in the communication. In addition, our results also provide a novel encoding-decoding scheme to achieve input-to-state practically stability (ISpS) for nonlinear continuous-time systems under appropriate assumptions.

eess.SY↗

arXiv2019

On the Convergence Properties of Social Hegselmann-Krause Dynamics

We study the convergence properties of Social Hegselmann-Krause dynamics, a {variant} of the Hegselmann-Krause (HK) model of opinion dynamics where a physical connectivity graph that accounts for the extrinsic factors that could prevent interaction between certain pairs of agents is incorporated. As opposed to the original HK dynamics (which terminate in finite time), we show that for any underlying connected and incomplete graph, under a certain mild assumption, the expected termination time of social HK dynamics is infinity. We then investigate the rate of convergence to the steady state, and provide bounds on the maximum $ε$-convergence time in terms of the properties of the physical connectivity graph. We extend this discussion and observe that for almost all $n$, there exists an $n$-vertex physical connectivity graph on which social HK dynamics may not even $ε$-converge to the steady state within a bounded time frame. We then provide nearly tight necessary and sufficient conditions for arbitrarily slow merging (a phenomenon that is essential for arbitrarily slow $ε$-convergence to the steady state). Using the necessary conditions, we show that complete $r$-partite graphs have bounded $ε$-convergence times.

math.OC↗

arXiv2019

Associative Convolutional Layers

Motivated by the necessity for parameter efficiency in distributed machine learning and AI-enabled edge devices, we provide a general and easy to implement method for significantly reducing the number of parameters of Convolutional Neural Networks (CNNs), during both the training and inference phases. We introduce a simple auxiliary neural network which can generate the convolutional filters of any CNN architecture from a low dimensional latent space. This auxiliary neural network, which we call "Convolutional Slice Generator" (CSG), is unique to the network and provides the association between its convolutional layers. During the training of the CNN, instead of training the filters of the convolutional layers, only the parameters of the CSG and their corresponding "code vectors" are trained. This results in a significant reduction of the number of parameters due to the fact that the CNN can be fully represented using only the parameters of the CSG, the code vectors, the fully connected layers, and the architecture of the CNN. We evaluate our approach by applying it to ResNet and DenseNet models when trained on CIFAR-10 and ImageNet datasets. While reducing the number of parameters by $\approx 2 \times$ on average, the accuracies of these networks remain within 1$\%$ of their original counterparts and in some cases there is an increase in the accuracy.

cs.LG↗

arXiv2019

The value of timing information in event-triggered control

We study event-triggered control for stabilization of unstable linear plants over rate-limited communication channels subject to unknown, bounded delay. On one hand, the timing of event triggering carries implicit information about the state of the plant. On the other hand, the delay in the communication channel causes information loss, as it makes the state information available at the controller out of date. Combining these two effects, we show a phase transition behavior in the transmission rate required for stabilization using a given event-triggering strategy. For small values of the delay, the timing information carried by the triggering events is substantial, and the system can be stabilized with any positive rate. When the delay exceeds a critical threshold, the timing information alone is not enough to achieve stabilization and the required rate grows. When the loss of information due to the communication delay perfectly compensates the implicit information carried by the triggering events, the delay equals the inverse of the entropy rate of the plant, and we obtain the same rate requirement prescribed by the data-rate theorem. When the delay is larger than this threshold, the required rate becomes larger than that required by the data-rate theorem. We also provide an explicit construction yielding a sufficient rate for stabilization, and generalize our results to vector systems. The results do not rely on any a priori probabilistic model of the delay or the initial conditions.

math.OC↗

arXiv2019

Online learning with feedback graphs and switching costs

We study online learning when partial feedback information is provided following every action of the learning process, and the learner incurs switching costs for changing his actions. In this setting, the feedback information system can be represented by a graph, and previous works studied the expected regret of the learner in the case of a clique (Expert setup), or disconnected single loops (Multi-Armed Bandits (MAB)). This work provides a lower bound on the expected regret in the Partial Information (PI) setting, namely for general feedback graphs --excluding the clique. Additionally, it shows that all algorithms that are optimal without switching costs are necessarily sub-optimal in the presence of switching costs, which motivates the need to design new algorithms. We propose two new algorithms: Threshold Based EXP3 and EXP3. SC. For the two special cases of symmetric PI setting and MAB, the expected regret of both of these algorithms is order optimal in the duration of the learning process. Additionally, Threshold Based EXP3 is order optimal in the switching cost, whereas EXP3. SC is not. Finally, empirical evaluations show that Threshold Based EXP3 outperforms the previously proposed order-optimal algorithms EXP3 SET in the presence of switching costs, and Batch EXP3 in the MAB setting with switching costs.

cs.LG↗

arXiv2018

Improved Intolerance Intervals and Size Bounds for a Schelling-Type Spin System

We consider a Schelling model of self-organized segregation in an open system that is equivalent to a zero-temperature Ising model with Glauber dynamics, or an Asynchronous Cellular Automaton (ACA) with extended Moore neighborhoods. Previous work has shown that if the intolerance parameter of the model $τ\in (\sim 0.488,\sim 0.512) \setminus \{1/2\}$, then for a sufficiently large neighborhood of interaction $N$, any particle will end up in an exponentially large monochromatic region almost surely. This paper extends the above result to the interval $τ\in (\sim 0.433,\sim 0.567) \setminus \{1/2\}$. We also improve the bounds on the size of the monochromatic region by exponential factors in $N$. Finally, we show that when particles are placed on the infinite lattice $\mathbb{Z}^2$ rather than on a flat torus, for the values of $τ$ mentioned above, sufficiently large $N$, and after a sufficiently long evolution time, any particle is contained in a large monochromatic region of size exponential in $N$, almost surely. The new proof, critically relies on a novel geometric construction related to the formation of the monochromatic region.

cs.SI↗

arXiv2018

Unifying the stochastic and the adversarial Bandits with Knapsack

This paper investigates the adversarial Bandits with Knapsack (BwK) online learning problem, where a player repeatedly chooses to perform an action, pays the corresponding cost, and receives a reward associated with the action. The player is constrained by the maximum budget $B$ that can be spent to perform actions, and the rewards and the costs of the actions are assigned by an adversary. This problem has only been studied in the restricted setting where the reward of an action is greater than the cost of the action, while we provide a solution in the general setting. Namely, we propose EXP3.BwK, a novel algorithm that achieves order optimal regret. We also propose EXP3++.BwK, which is order optimal in the adversarial BwK setup, and incurs an almost optimal expected regret with an additional factor of $\log(B)$ in the stochastic BwK setup. Finally, we investigate the case of having large costs for the actions (i.e., they are comparable to the budget size $B$), and show that for the adversarial setting, achievable regret bounds can be significantly worse, compared to the case of having costs bounded by a constant, which is a common assumption within the BwK literature.

cs.LG↗

arXiv2018

Event-triggered stabilization of disturbed linear systems over digital channels

We present an event-triggered control strategy for stabilizing a scalar, continuous-time, time-invariant, linear system over a digital communication channel having bounded delay, and in the presence of bounded system disturbance. We propose an encoding-decoding scheme, and determine lower bounds on the packet size and on the information transmission rate which are sufficient for stabilization. We show that for small values of the delay, the timing information implicit in the triggering events is enough to stabilize the system with any positive rate. In contrast, when the delay increases beyond a critical threshold, the timing information alone is not enough to stabilize the system and the transmission rate begins to increase. Finally, large values of the delay require transmission rates higher than what prescribed by the classic data-rate theorem. The results are numerically validated using a linearized model of an inverted pendulum.

math.OC↗

arXiv2018

Self-organized Segregation on the Grid

We consider an agent-based model in which two types of agents interact locally over a graph and have a common intolerance threshold $τ$ for changing their types with exponentially distributed waiting times. The model is equivalent to an unperturbed Schelling model of self-organized segregation, an Asynchronous Cellular Automata (ACA) with extended Moore neighborhoods, or a zero-temperature Ising model with Glauber dynamics, and has applications in the analysis of social and biological networks, and spin glasses systems. Some rigorous results were recently obtained in the theoretical computer science literature, and this work provides several extensions. We enlarge the intolerance interval leading to the formation of large segregated regions of agents of a single type from the known size $ε>0$ to size $\approx 0.134$. Namely, we show that for $0.433 < τ< 1/2$ (and by symmetry $1/2<τ<0.567$), the expected size of the largest segregated region containing an arbitrary agent is exponential in the size of the neighborhood. We further extend the interval leading to large segregated regions to size $\approx 0.312$ considering "almost segregated" regions, namely regions where the ratio of the number of agents of one type and the number of agents of the other type vanishes quickly as the size of the neighborhood grows. In this case, we show that for $0.344 < τ\leq 0.433$ (and by symmetry for $0.567 \leq τ<0.656$) the expected size of the largest almost segregated region containing an arbitrary agent is exponential in the size of the neighborhood. The exponential bounds that we provide also imply that complete segregation, where agents of a single type cover the whole grid, does not occur with high probability for $p=1/2$ and the range of tolerance considered.

cs.SI↗

arXiv2017

Time-triggering versus event-triggering control over communication channels

Time-triggered and event-triggered control strategies for stabilization of an unstable plant over a rate-limited communication channel subject to unknown, bounded delay are studied and compared. Event triggering carries implicit information, revealing the state of the plant. However, the delay in the communication channel causes information loss, as it makes the state information out of date. There is a critical delay value, when the loss of information due to the communication delay perfectly compensates the implicit information carried by the triggering events. This occurs when the maximum delay equals the inverse of the entropy rate of the plant. In this context, extensions of our previous results for event triggering strategies are presented for vector systems and are compared with the data-rate theorem for time-triggered control, that is extended here to a setting with unknown delay.

math.OC↗

arXiv2017

Deterministic coding theorems for blind sensing: optimal measurement rate and fractal dimension

Completely blind sensing is the problem of recovering bandlimited signals from measurements, without any spectral information beside an upper bound on the measure of the whole support set in the frequency domain. Determining the number of measurements necessary and sufficient for reconstruction has been an open problem, and usually partially blind sensing is performed, assuming to have some partial spectral information available a priori. In this paper, the minimum number of measurements that guarantees perfect recovery in the absence of measurement error, and robust recovery in the presence of measurement error, is determined in a completely blind setting. Results show that a factor of two in the measurement rate is the price pay for blindness, compared to reconstruction with full spectral knowledge. The minimum number of measurements is also related to the fractal (Minkowski-Bouligand) dimension of a discrete approximating set, defined in terms of the Kolmogorov $ε$-entropy. These results are analogous to a deterministic coding theorem, where an operational quantity defined in terms of minimum measurement rate is shown to be equal to an information-theoretic one. A comparison with parallel results in compressed sensing is illustrated, where the relevant dimensionality notion in a stochastic setting is the information (Rényi) dimension, defined in terms of the Shannon entropy.

cs.IT↗